First-Shot Unsupervised Anomalous Sound Detection for Machine Condition Monitoring

Challenge results
We have released the ground truth labels and evaluator for the evaluation dataset, in addition to the submitted raw anomaly scores. More detailed information on the ground truth labels and the evaluator can be found in the task description page.

Task description

The goal of this task is to identify whether a machine is normal or anomalous using only normal sound data under domain shifted conditions. One major difference from DCASE 2022 Task 2 is that the set of machine types are completely different between the development dataset and evaluation dataset. Therefore, the participants are expected to develop a system that can handle completely new machine types.

More detailed task description can be found in the task description page

Teams ranking

Table including only the best performing system per submitting team.

Rank Submission Information Evaluation Dataset Development Dataset
Submission Code Technical
Report 		Official
Rank 		Official
Score 		ToyDrone
(AUC) 		ToyDrone
(pAUC) 		ToyNscale
(AUC) 		ToyNscale
(pAUC) 		ToyTank
(AUC) 		ToyTank
(pAUC) 		Vacuum
(AUC) 		Vacuum
(pAUC) 		Bandsaw
(AUC) 		Bandsaw
(pAUC) 		Grinder
(AUC) 		Grinder
(pAUC) 		Shaker
(AUC) 		Shaker
(pAUC) 		ToyCar
(AUC) 		ToyCar
(pAUC) 		ToyTrain
(AUC) 		ToyTrain
(pAUC) 		Bearing
(AUC) 		Bearing
(pAUC) 		Fan
(AUC) 		Fan
(pAUC) 		Gearbox
(AUC) 		Gearbox
(pAUC) 		Slider
(AUC) 		Slider
(pAUC) 		Valve
(AUC) 		Valve
(pAUC)
DCASE2023_baseline_task2_MAHALA DCASE2023baseline2023 24 61.05082186925268 ± 0.0015218757062443913 58.93 51.42 50.73 50.89 57.89 53.84 86.84 65.32 69.10 57.54 60.19 59.55 72.28 62.33 59.20 49.18 48.73 48.05 59.77 50.68 61.89 58.42 71.58 54.84 79.25 56.18 53.74 51.28
Du_NERCSLIP_task2_2 DuNERCSLIP2023 19 61.765486226672074 ± 0.0017959994163787177 58.06 51.47 86.84 65.37 61.29 57.58 82.05 60.84 47.58 49.92 49.06 49.21 93.24 80.78 68.86 59.47 68.47 51.63 84.62 76.68 89.21 77.32 81.68 66.53 97.66 90.16 92.66 85.37
He_XJU_task2_4 HeXJU2023 74 48.17910227573888 ± 0.0014803390407048121 39.26 50.11 51.79 52.74 47.34 50.37 48.34 52.53 36.68 49.55 65.85 58.46 47.06 49.51 44.14 75.00 54.06 49.36 67.04 56.78 46.83 47.84 53.77 52.73 92.79 83.42 44.28 52.21
Lv_HUAKONG_task2_4 LvHUAKONG2023 2 66.38618902139308 ± 0.001763447255809211 54.84 49.37 82.71 57.00 74.80 63.79 93.66 87.42 58.48 50.30 66.69 61.22 74.24 65.24 65.47 49.47 64.82 49.32 78.80 62.26 65.97 56.32 82.28 62.47 94.74 76.68 73.66 53.68
Jiang_THUEE_task2_1 JiangTHUEE2023 4 65.40305914562828 ± 0.0016954969066200025 55.83 49.74 73.44 61.63 63.03 59.74 81.98 76.42 71.10 56.64 62.18 62.41 75.99 64.68 58.40 50.37 49.77 48.32 66.15 51.84 88.20 76.32 76.38 57.68 88.27 66.37 67.90 53.58
JiaJun_HFUU_task2_3 JiaJunHFUU2023 27 59.539455870919 ± 0.0017136456379770644 43.91 48.79 83.60 64.53 53.54 55.63 79.38 73.95 71.25 57.83 59.03 55.84 55.92 49.32 48.90 48.68 51.28 49.10 68.18 52.00 80.58 61.89 84.92 65.31 95.10 89.57 81.82 55.84
Zhang_DKU_task2_2 ZhangDKU2023 57 53.943211217441004 ± 0.001648641037227489 58.31 52.37 75.26 64.11 37.34 52.68 43.69 56.00 55.42 55.05 63.06 57.10 58.23 50.72 52.78 51.79 55.46 54.74 61.64 56.84 68.82 58.11 74.70 65.89 92.64 69.89 67.48 49.26
Zhou_SHNU_task2_3 ZhouSHNU2023 10 63.64485714595981 ± 0.0017183511378647829 61.10 55.74 62.23 52.11 68.66 59.53 77.05 63.53 69.13 51.99 69.04 61.51 68.83 55.94 61.90 51.05 57.18 48.36 63.39 51.26 74.13 63.78 65.22 54.78 77.07 53.26 52.48 51.00
Zhang_BIT_task2_1 ZhangBIT2023 28 59.48866414964231 ± 0.001496880906985829 52.05 51.89 62.01 57.21 64.18 57.32 56.81 60.47 62.03 50.09 61.76 61.32 71.55 61.06 52.10 63.75 59.65 55.80 58.50 63.50 72.80
Liu_CQUPT_task2_1 LiuCQUPT2023 44 56.00318391857601 ± 0.0017690559303198009 48.33 48.79 63.51 55.53 55.68 57.84 43.63 57.74 55.53 51.54 69.44 62.70 65.54 60.40 58.54 48.47 62.40 49.74 70.68 61.68 59.66 51.73 74.24 56.89 92.02 68.11 68.34 53.36
Atmaja_AIST_task2_4 AtmajaAIST2023 50 55.0920471984782 ± 0.0013534875706585426 55.55 54.00 50.32 53.00 54.35 51.84 74.99 64.11 53.39 50.31 48.09 48.29 63.21 54.28 56.55 48.79 56.26 50.16 50.51 50.71 50.01 51.37 58.59 50.87 51.85 50.71 48.06 49.97
Wilkinghoff_FKIE_task2_1 WilkinghoffFKIE2023 5 64.91145175990695 ± 0.0017818544158040373 53.90 50.21 87.14 76.58 63.43 62.21 83.26 74.00 66.06 52.87 67.10 62.11 65.91 50.24 60.66 48.00 58.12 48.37 75.48 51.42 80.22 52.32 82.66 65.21 94.02 72.68 88.98 55.62
Jiang_PSH_task2_2 JiangPSH2023 47 55.61393665575548 ± 0.001453889360427255 57.66 50.68 58.27 56.11 48.60 57.05 70.54 66.74 47.05 48.24 63.93 56.18 54.66 49.72 52.97 51.68 55.25 52.42 64.03 51.79 51.17 55.37 78.20 54.00 96.37 83.26 61.39 54.47
Wu_qdreamer_task2_3 Wuqdreamer2023 29 59.262985023209346 ± 0.001379038594802009 45.85 52.53 79.02 60.26 69.46 57.89 56.76 65.26 55.48 50.81 60.25 54.21 69.44 58.87 67.49 49.89 61.95 53.53 74.63 52.11 73.19 63.21 75.79 65.58 83.87 62.53 67.40 57.68
Xiao_NJUPT_task2_1 XiaoNJUPT2023 38 57.61233604271262 ± 0.00148382196939156 65.63 50.89 59.59 52.21 68.27 57.68 55.90 63.05 53.97 48.72 58.29 58.16 57.78 50.77 63.22 53.31 62.05 63.24 65.28 56.28 70.36 59.78 74.53 70.82 85.69 70.19 72.85 57.13
Jie_IESEFPT_task2_2 JieIESEFPT2023 1 66.96865050141963 ± 0.00180162797332972 58.03 51.58 89.03 77.74 60.33 61.53 96.18 85.32 65.66 53.35 66.63 62.45 68.08 55.97 57.68 42.73 56.56 47.47 73.84 51.31 86.96 61.22 82.13 63.43 97.12 82.81 93.38 73.02
Gou_UESTC_task2_3 GouUESTC2023 73 48.68995653342131 ± 0.0015180040461601286 42.32 48.47 56.72 50.11 43.96 54.47 41.29 49.42 55.72 52.61 48.24 49.51 51.59 49.14 50.82 51.00 51.48 49.68 54.94 51.26 62.13 49.84 56.42 54.11 72.76 75.63 47.36 52.26
Tanaka_GU_task2_3 TanakaGU2023 49 55.25265431943579 ± 0.0013817138477153071 37.89 48.21 60.97 52.74 69.38 59.11 59.42 62.84 52.13 51.25 60.02 55.39 60.33 58.62 56.44 49.58 60.98 50.11 63.36 54.42 47.60 58.32 58.96 51.58 57.50 58.95 47.26 50.11
Fujimura_NU_task2_1 FujimuraNU2023 54 54.70129260730897 ± 0.0017335695817680035 33.60 49.32 71.36 61.47 57.96 54.47 58.38 61.37 59.03 53.75 61.81 61.08 52.00 59.84 60.70 51.53 61.16 48.58 65.60 56.26 72.32 70.32 82.78 64.26 96.14 80.53 97.62 78.95
Bai_JLESS_task2_3 BaiJLESS2023 6 64.10430038433627 ± 0.0015312095360472697 51.44 50.89 59.85 51.16 70.05 59.58 81.46 69.47 74.51 55.65 67.07 63.03 78.30 63.37 62.47 49.96 53.89 48.16 62.95 51.79 84.85 68.30 75.31 56.21 83.31 55.11 53.97 50.95
Guan_HEU_task2_4 GuanHEU2023 14 63.50321347349609 ± 0.0016921801501565013 62.93 52.05 68.94 54.21 66.41 60.63 79.47 72.47 57.22 50.76 62.38 54.96 78.46 61.47 63.04 50.21 56.96 48.95 67.71 54.84 66.97 56.05 79.49 60.58 91.91 71.05 89.35 60.05
Hauser_JKU_task2_1 HauserJKU2023 86 41.40741259250251 ± 0.001374452454520565 40.70 48.47 36.58 48.74 37.85 50.32 25.95 47.89 52.84 51.26 41.91 49.08 44.11 48.23 46.18 48.91 49.33 49.53 40.02 49.34 48.18 58.11 43.10 49.76 52.08 51.57 64.38 58.85
LEE_KNU_task2_2 LEEKNU2023 84 44.231914616941665 ± 0.00130457675996216 40.03 50.21 42.70 51.58 38.82 51.68 35.20 49.53 43.53 47.37 46.42 48.50 49.01 52.08 46.38 51.47 47.74 48.27 70.84 50.58 65.31 52.16 78.20 51.58 82.07 51.90 97.06 97.57
QianXuHu_BITNUDT_task2_3 QianXuHuBITNUDT2023 31 59.06204701591861 ± 0.0015102887361449933 57.76 53.00 46.69 51.53 64.75 59.42 72.73 62.58 63.37 53.03 57.77 59.02 69.93 55.41 59.69 51.16 60.55 48.84 59.66 51.21 71.96 64.32 73.46 58.89 78.89 59.42 65.05 55.00


Supplementary metrics (recall, precision, and F1 score)

Rank Submission Information Evaluation Dataset
Submission Code Technical
Report 		Official
Rank 		ToyDrone
(F1 score) 		ToyDrone
(Recall) 		ToyDrone
(Precision) 		ToyNscale
(F1 score) 		ToyNscale
(Recall) 		ToyNscale
(Precision) 		ToyTank
(F1 score) 		ToyTank
(Recall) 		ToyTank
(Precision) 		Vacuum
(F1 score) 		Vacuum
(Recall) 		Vacuum
(Precision) 		Bandsaw
(F1 score) 		Bandsaw
(Recall) 		Bandsaw
(Precision) 		Grinder
(F1 score) 		Grinder
(Recall) 		Grinder
(Precision) 		Shaker
(F1 score) 		Shaker
(Recall) 		Shaker
(Precision)
DCASE2023_baseline_task2_MAHALA DCASE2023baseline2023 24 15.56 8.89 62.50 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 53.38 100.00 36.41 43.65 100.00 27.92 66.06 100.00 49.32
Du_NERCSLIP_task2_2 DuNERCSLIP2023 19 60.13 59.93 60.34 73.90 73.25 74.56 58.08 57.72 58.45 79.08 78.38 79.79 46.99 47.88 46.13 33.33 47.06 25.81 83.70 83.52 83.88
He_XJU_task2_4 HeXJU2023 74 21.65 14.81 40.16 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
Lv_HUAKONG_task2_4 LvHUAKONG2023 2 50.70 50.21 51.20 77.54 77.54 77.54 66.34 66.27 66.41 87.74 87.82 87.66 48.30 57.14 41.83 48.41 66.67 38.00 66.92 66.45 67.40
Jiang_THUEE_task2_1 JiangTHUEE2023 4 59.54 55.73 63.91 66.40 63.24 69.90 58.73 51.10 69.05 71.19 66.44 76.67 59.96 71.39 51.68 45.44 63.15 35.49 65.28 65.57 64.98
JiaJun_HFUU_task2_3 JiaJunHFUU2023 27 11.80 6.55 60.00 38.52 25.08 83.01 0.00 0.00 0.00 38.71 24.00 100.00 44.28 32.26 70.59 39.77 32.23 51.92 24.91 16.85 47.78
Zhang_DKU_task2_2 ZhangDKU2023 57 0.00 0.00 0.00 7.47 3.89 92.50 0.00 0.00 0.00 0.00 0.00 0.00 35.79 28.64 47.71 10.26 5.80 44.44 12.96 7.44 50.00
Zhou_SHNU_task2_3 ZhouSHNU2023 10 41.16 31.49 59.39 49.26 42.42 58.73 58.23 51.31 67.31 62.19 50.51 80.90 54.93 56.48 53.46 50.10 54.24 46.56 57.52 51.28 65.49
Zhang_BIT_task2_1 ZhangBIT2023 28 53.82 46.34 64.18 56.96 56.28 57.67 57.38 57.38 57.38 32.27 21.28 66.67 52.75 63.06 45.34 45.51 63.15 35.57 59.37 60.38 58.38
Liu_CQUPT_task2_1 LiuCQUPT2023 44 48.11 47.12 49.14 54.62 51.53 58.10 23.97 14.79 63.12 19.19 11.27 64.79 47.50 55.47 41.53 52.73 71.79 41.67 58.26 58.39 58.14
Atmaja_AIST_task2_4 AtmajaAIST2023 50 0.00 0.00 0.00 62.42 73.85 54.05 0.00 0.00 0.00 67.57 100.00 51.02 38.61 40.22 37.11 38.46 47.21 32.44 58.72 62.47 55.40
Wilkinghoff_FKIE_task2_1 WilkinghoffFKIE2023 5 67.21 78.91 58.53 72.90 75.00 70.92 61.93 70.13 55.45 73.22 91.30 61.12 54.42 54.79 54.05 50.00 56.14 45.07 59.34 54.55 65.06
Jiang_PSH_task2_2 JiangPSH2023 47 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
Wu_qdreamer_task2_3 Wuqdreamer2023 29 6.77 3.91 25.21 71.57 94.74 57.51 66.37 85.06 54.41 0.00 0.00 0.00 54.22 78.26 41.47 45.82 68.29 34.47 62.74 75.67 53.58
Xiao_NJUPT_task2_1 XiaoNJUPT2023 38 66.52 83.81 55.14 66.59 82.29 55.92 65.24 63.82 66.73 46.22 35.51 66.19 42.22 50.41 36.32 44.72 83.99 30.47 64.78 85.92 51.99
Jie_IESEFPT_task2_2 JieIESEFPT2023 1 69.48 85.61 58.46 78.79 85.06 73.38 61.71 70.13 55.10 80.32 100.00 67.11 53.93 55.60 52.36 48.48 52.58 44.98 67.39 74.55 61.48
Gou_UESTC_task2_3 GouUESTC2023 73 13.78 7.69 66.67 55.56 55.71 55.40 44.83 34.87 62.77 13.53 7.68 56.80 48.43 57.67 41.75 38.22 52.63 30.00 50.32 50.57 50.08
Tanaka_GU_task2_3 TanakaGU2023 49 7.27 3.91 51.43 53.45 45.04 65.73 62.50 62.60 62.41 31.17 21.43 57.14 41.44 46.68 37.26 40.29 49.12 34.15 46.54 39.18 57.31
Fujimura_NU_task2_1 FujimuraNU2023 54 19.01 11.29 60.00 61.64 52.94 73.77 46.69 35.51 68.15 41.09 30.21 64.19 55.88 63.96 49.61 47.24 64.21 37.36 53.66 53.15 54.18
Bai_JLESS_task2_3 BaiJLESS2023 6 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
Guan_HEU_task2_4 GuanHEU2023 14 52.84 46.47 61.25 59.04 53.33 66.12 55.85 45.38 72.60 63.84 50.03 88.17 38.77 39.69 37.89 45.09 50.72 40.58 69.96 63.55 77.80
Hauser_JKU_task2_1 HauserJKU2023 86 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 53.38 100.00 36.41 43.65 100.00 27.92 66.06 100.00 49.32
LEE_KNU_task2_2 LEEKNU2023 84 62.39 80.95 50.75 59.60 72.00 50.85 59.41 75.00 49.18 64.14 86.36 51.01 50.49 68.29 40.05 42.64 75.36 29.73 56.47 64.51 50.21
QianXuHu_BITNUDT_task2_3 QianXuHuBITNUDT2023 31 0.00 0.00 0.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 53.56 100.00 36.58 43.65 100.00 27.92 68.79 98.08 52.98



Systems ranking

Rank Submission Information Evaluation Dataset Development Dataset
Submission Code Technical
Report 		Official
Rank 		Official
Score 		ToyDrone
(AUC) 		ToyDrone
(pAUC) 		ToyNscale
(AUC) 		ToyNscale
(pAUC) 		ToyTank
(AUC) 		ToyTank
(pAUC) 		Vacuum
(AUC) 		Vacuum
(pAUC) 		Bandsaw
(AUC) 		Bandsaw
(pAUC) 		Grinder
(AUC) 		Grinder
(pAUC) 		Shaker
(AUC) 		Shaker
(pAUC) 		ToyCar
(AUC) 		ToyCar
(pAUC) 		ToyTrain
(AUC) 		ToyTrain
(pAUC) 		Bearing
(AUC) 		Bearing
(pAUC) 		Fan
(AUC) 		Fan
(pAUC) 		Gearbox
(AUC) 		Gearbox
(pAUC) 		Slider
(AUC) 		Slider
(pAUC) 		Valve
(AUC) 		Valve
(pAUC)
DCASE2023_baseline_task2_MAHALA DCASE2023baseline2023 24 61.05082186925268 ± 0.0015218757062443913 58.93 51.42 50.73 50.89 57.89 53.84 86.84 65.32 69.10 57.54 60.19 59.55 72.28 62.33 59.20 49.18 48.73 48.05 59.77 50.68 61.89 58.42 71.58 54.84 79.25 56.18 53.74 51.28
DCASE2023_baseline_task2_MSE DCASE2023baseline2023 30 59.25469043549957 ± 0.0015318988799038432 65.84 53.68 58.49 51.79 68.20 58.26 59.87 59.47 56.01 50.91 61.97 58.46 62.02 54.92 59.36 52.93 58.03 48.28 60.85 50.30 54.02 58.28 61.01 53.44 59.56 57.04 53.56 51.12
Du_NERCSLIP_task2_1 DuNERCSLIP2023 21 61.40265030314117 ± 0.0017835401670258867 57.93 51.11 86.17 64.84 60.94 56.63 82.86 62.11 47.04 49.37 47.33 49.40 94.23 82.87 70.31 58.95 70.21 53.32 84.78 77.11 89.04 76.11 84.98 67.89 97.81 90.89 92.66 85.37
Du_NERCSLIP_task2_2 DuNERCSLIP2023 19 61.765486226672074 ± 0.0017959994163787177 58.06 51.47 86.84 65.37 61.29 57.58 82.05 60.84 47.58 49.92 49.06 49.21 93.24 80.78 68.86 59.47 68.47 51.63 84.62 76.68 89.21 77.32 81.68 66.53 97.66 90.16 92.66 85.37
Du_NERCSLIP_task2_3 DuNERCSLIP2023 20 61.72668688068389 ± 0.0016960833303502675 58.21 52.05 86.38 65.05 61.54 58.00 80.72 60.16 47.95 50.54 50.51 48.11 91.09 76.08 71.01 58.00 68.11 52.95 83.81 75.79 86.86 76.58 81.03 66.68 97.00 88.53 92.66 85.37
Du_NERCSLIP_task2_4 DuNERCSLIP2023 23 61.33284074574933 ± 0.001706784911538521 58.48 52.16 85.77 64.00 61.04 58.74 79.74 59.74 47.92 51.17 51.00 47.75 88.15 69.74 68.01 57.79 72.84 54.32 81.56 72.00 86.37 71.74 83.82 67.42 96.96 87.53 92.66 85.37
He_XJU_task2_1 HeXJU2023 78 46.89167264620427 ± 0.0014839978080730181 39.46 49.21 51.30 52.74 52.85 50.16 38.53 51.00 41.23 47.96 53.18 50.84 46.71 49.64 47.32 50.10 44.52 48.68 49.24 48.26 47.88 49.89 51.43 50.36 79.46 69.11 51.18 55.10
He_XJU_task2_2 HeXJU2023 83 44.80907187312061 ± 0.001437121781209372 38.54 50.00 45.40 50.89 48.55 51.21 27.55 47.95 48.29 48.28 51.32 52.09 52.46 48.85 52.57 51.21 52.89 48.74 72.25 55.89 46.09 50.10 58.16 52.84 76.52 70.10 48.89 49.42
He_XJU_task2_3 HeXJU2023 80 46.41086559024494 ± 0.0015280006063045325 41.07 49.74 30.07 47.58 49.56 52.11 40.44 53.32 46.28 51.60 49.37 53.13 68.49 57.94 49.02 49.42 56.37 48.68 59.59 52.84 43.58 48.78 51.81 51.10 84.62 73.15 57.11 53.31
He_XJU_task2_4 HeXJU2023 74 48.17910227573888 ± 0.0014803390407048121 39.26 50.11 51.79 52.74 47.34 50.37 48.34 52.53 36.68 49.55 65.85 58.46 47.06 49.51 44.14 75.00 54.06 49.36 67.04 56.78 46.83 47.84 53.77 52.73 92.79 83.42 44.28 52.21
Lv_HUAKONG_task2_1 LvHUAKONG2023 11 63.641026999638264 ± 0.0016956362933551541 52.86 49.47 74.94 56.95 68.38 62.79 85.48 70.32 54.24 51.15 66.93 62.16 73.46 65.50 63.52 48.95 63.25 52.74 76.98 57.79 69.51 55.11 87.23 72.79 94.02 71.37 78.94 54.00
Lv_HUAKONG_task2_2 LvHUAKONG2023 15 62.91199838369852 ± 0.001748368530129158 52.56 49.32 68.50 52.21 64.91 62.79 79.26 63.95 56.87 51.76 68.77 63.44 76.51 71.23 62.91 50.56 58.26 49.79 74.84 53.95 74.04 61.16 86.16 75.53 93.89 70.53 73.77 57.87
Lv_HUAKONG_task2_3 LvHUAKONG2023 8 63.85811949412737 ± 0.001663717465843232 53.38 49.84 77.54 56.79 66.34 58.21 84.96 70.32 56.34 50.11 70.01 61.98 74.51 63.13 59.14 48.79 62.28 50.42 80.32 67.21 72.50 57.16 89.64 76.53 94.32 72.84 76.61 52.42
Lv_HUAKONG_task2_4 LvHUAKONG2023 2 66.38618902139308 ± 0.001763447255809211 54.84 49.37 82.71 57.00 74.80 63.79 93.66 87.42 58.48 50.30 66.69 61.22 74.24 65.24 65.47 49.47 64.82 49.32 78.80 62.26 65.97 56.32 82.28 62.47 94.74 76.68 73.66 53.68
Jiang_THUEE_task2_1 JiangTHUEE2023 4 65.40305914562828 ± 0.0016954969066200025 55.83 49.74 73.44 61.63 63.03 59.74 81.98 76.42 71.10 56.64 62.18 62.41 75.99 64.68 58.40 50.37 49.77 48.32 66.15 51.84 88.20 76.32 76.38 57.68 88.27 66.37 67.90 53.58
Jiang_THUEE_task2_2 JiangTHUEE2023 35 58.135795444298886 ± 0.0018171205740200168 34.32 49.11 69.55 55.42 59.84 54.37 78.16 71.37 60.16 51.12 63.07 61.40 70.77 65.33 61.62 49.53 60.52 49.53 71.92 56.00 81.28 65.37 84.37 68.16 96.76 84.21 73.23 58.80
Jiang_THUEE_task2_3 JiangTHUEE2023 7 63.89749272780968 ± 0.0017249015968282557 49.63 48.89 77.66 52.53 69.47 55.89 81.87 73.00 66.53 50.75 66.05 61.77 75.29 64.50 63.24 48.63 62.66 48.53 75.21 56.53 86.96 62.89 86.29 68.79 96.83 83.74 72.95 54.47
Jiang_THUEE_task2_4 JiangTHUEE2023 17 62.38070966737226 ± 0.0017055328702134229 51.56 49.79 71.14 53.16 62.07 55.42 77.26 65.26 63.91 50.98 65.01 63.08 75.44 65.23 60.69 48.42 62.17 50.58 73.28 65.63 88.11 63.58 89.64 73.89 96.28 81.68 78.56 55.79
JiaJun_HFUU_task2_1 JiaJunHFUU2023 33 58.169557409440074 ± 0.001718520073442323 36.99 49.32 83.60 64.53 53.54 55.63 79.38 73.95 71.25 57.83 59.03 55.84 55.92 49.32 49.76 48.63 48.95 49.21 67.98 51.63 81.80 61.57 84.48 66.84 94.44 87.42 86.12 65.21
JiaJun_HFUU_task2_2 JiaJunHFUU2023 33 58.169557409440074 ± 0.001718520073442323 36.99 49.32 83.60 64.53 53.54 55.63 79.38 73.95 71.25 57.83 59.03 55.84 55.92 49.32 50.86 48.68 49.90 49.15 68.26 52.15 81.84 66.00 85.08 66.84 94.92 89.21 84.22 58.47
JiaJun_HFUU_task2_3 JiaJunHFUU2023 27 59.539455870919 ± 0.0017136456379770644 43.91 48.79 83.60 64.53 53.54 55.63 79.38 73.95 71.25 57.83 59.03 55.84 55.92 49.32 48.90 48.68 51.28 49.10 68.18 52.00 80.58 61.89 84.92 65.31 95.10 89.57 81.82 55.84
JiaJun_HFUU_task2_4 JiaJunHFUU2023 41 56.93963532020672 ± 0.00162923369781846 36.99 49.32 83.60 64.53 53.54 55.63 79.38 73.95 59.85 50.64 59.03 55.84 55.92 49.32 49.24 48.84 52.41 48.84 68.52 52.41 80.42 61.73 84.48 65.00 94.94 88.73 79.58 55.68
Zhang_DKU_task2_1 ZhangDKU2023 76 47.85601959825719 ± 0.001486695076025454 44.89 49.63 54.90 51.42 48.83 51.84 37.05 49.68 47.23 50.77 54.78 53.80 42.65 50.38 48.76 49.05 49.65 47.79 65.58 56.84 60.70 57.26 68.00 54.53 96.74 95.58 65.78 53.68
Zhang_DKU_task2_2 ZhangDKU2023 57 53.943211217441004 ± 0.001648641037227489 58.31 52.37 75.26 64.11 37.34 52.68 43.69 56.00 55.42 55.05 63.06 57.10 58.23 50.72 52.78 51.79 55.46 54.74 61.64 56.84 68.82 58.11 74.70 65.89 92.64 69.89 67.48 49.26
Zhang_DKU_task2_3 ZhangDKU2023 65 50.362219485218304 ± 0.0014691134337457292 44.61 47.74 54.50 54.11 44.85 51.37 40.48 51.11 53.42 53.11 64.86 57.20 51.38 51.34 49.12 49.68 44.98 47.37 60.32 60.00 69.10 61.68 70.52 69.47 73.74 66.11 68.24 63.37
Zhang_DKU_task2_4 ZhangDKU2023 76 47.85601959825719 ± 0.001486695076025454 44.89 49.63 54.90 51.42 48.83 51.84 37.05 49.68 47.23 50.77 54.78 53.80 42.65 50.38 51.50 52.21 53.92 51.16 65.72 57.26 63.66 57.89 75.00 56.42 94.50 82.11 66.02 48.84
Zhou_SHNU_task2_1 ZhouSHNU2023 32 58.542095543559356 ± 0.0015955525547135157 52.27 51.37 70.86 64.16 43.40 51.05 64.34 49.79 69.13 51.99 69.04 61.51 68.83 55.94 64.59 50.15 58.73 51.78 63.65 51.10 72.94 56.42 60.50 53.22 68.53 51.63 45.84 49.78
Zhou_SHNU_task2_2 ZhouSHNU2023 69 49.78071871290905 ± 0.0015131690089389166 52.27 51.37 70.86 64.16 43.40 51.05 64.34 49.79 37.86 50.28 42.93 49.34 45.42 50.36 64.59 50.15 58.73 51.78 63.65 51.10 72.94 56.42 60.50 53.22 68.53 51.63 45.84 49.78
Zhou_SHNU_task2_3 ZhouSHNU2023 10 63.64485714595981 ± 0.0017183511378647829 61.10 55.74 62.23 52.11 68.66 59.53 77.05 63.53 69.13 51.99 69.04 61.51 68.83 55.94 61.90 51.05 57.18 48.36 63.39 51.26 74.13 63.78 65.22 54.78 77.07 53.26 52.48 51.00
Zhou_SHNU_task2_1 ZhouSHNU2023 32 58.542095543559356 ± 0.0015955525547135157 52.27 51.37 70.86 64.16 43.40 51.05 64.34 49.79 69.13 51.99 69.04 61.51 68.83 55.94 64.59 50.15 58.73 51.78 63.65 51.10 72.94 56.42 60.50 53.22 68.53 51.63 45.84 49.78
Zhang_BIT_task2_1 ZhangBIT2023 28 59.48866414964231 ± 0.001496880906985829 52.05 51.89 62.01 57.21 64.18 57.32 56.81 60.47 62.03 50.09 61.76 61.32 71.55 61.06 52.10 63.75 59.65 55.80 58.50 63.50 72.80
Zhang_BIT_task2_2 ZhangBIT2023 56 54.210315178401395 ± 0.0013985070411561664 41.73 49.05 53.01 52.16 48.77 51.63 51.89 52.79 67.89 51.38 62.10 58.67 69.16 58.08 53.75 44.45 61.50 74.75 71.10 75.45 53.60
Zhang_BIT_task2_3 ZhangBIT2023 67 49.943548299651766 ± 0.0014282994275963807 45.50 48.63 50.24 51.68 49.69 48.21 47.06 49.95 51.91 50.85 58.70 52.42 48.11 49.08 65.55 54.95 71.25 70.65 54.40 63.35 63.60
Zhang_BIT_task2_4 ZhangBIT2023 43 56.27066126406969 ± 0.0016641694588265764 48.03 51.05 68.37 55.47 63.55 54.58 52.63 55.47 52.48 48.76 58.10 61.47 62.92 56.25 62.95 61.00 73.75 77.55 65.75 70.90 46.60
Liu_CQUPT_task2_1 LiuCQUPT2023 44 56.00318391857601 ± 0.0017690559303198009 48.33 48.79 63.51 55.53 55.68 57.84 43.63 57.74 55.53 51.54 69.44 62.70 65.54 60.40 58.54 48.47 62.40 49.74 70.68 61.68 59.66 51.73 74.24 56.89 92.02 68.11 68.34 53.36
Liu_CQUPT_task2_2 LiuCQUPT2023 64 50.41922704617341 ± 0.00151277878553744 47.77 48.74 48.33 49.58 39.21 50.26 37.84 52.16 62.88 54.00 55.78 56.16 73.86 53.84 52.46 51.71 54.68 49.95 59.14 51.10 74.22 50.31 84.54 55.26 98.48 91.47 60.72 53.47
Liu_CQUPT_task2_3 LiuCQUPT2023 48 55.59389634677413 ± 0.001558902874346492 47.86 48.63 60.13 53.37 51.00 56.58 43.20 56.74 62.00 54.31 64.71 59.42 73.23 59.31 56.20 51.10 59.18 48.89 66.50 53.05 66.84 51.57 85.04 53.31 98.20 89.53 63.56 53.95
Liu_CQUPT_task2_4 LiuCQUPT2023 45 55.66677560102276 ± 0.0015322461322400422 47.88 48.58 59.32 52.63 51.94 56.95 43.41 57.11 61.51 54.38 64.85 59.29 73.29 60.15 56.46 50.89 59.18 49.00 67.80 54.15 69.12 51.36 84.42 53.47 97.94 87.95 63.98 54.26
Atmaja_AIST_task2_1 AtmajaAIST2023 53 54.897809500433034 ± 0.0013673077294584605 55.35 54.11 50.14 53.11 55.02 52.32 71.41 63.32 53.59 50.26 48.32 48.29 62.66 53.48 56.85 48.68 55.96 50.16 50.75 50.29 50.69 50.79 58.87 50.97 51.70 50.45 48.27 50.03
Atmaja_AIST_task2_2 AtmajaAIST2023 51 55.04922229013841 ± 0.0013864114692666522 55.62 54.00 51.25 54.05 54.57 51.05 72.81 63.74 53.35 50.26 48.05 48.29 63.20 53.43 56.71 48.63 56.17 49.89 50.26 50.45 50.30 52.00 58.73 50.82 51.81 50.82 48.02 49.97
Atmaja_AIST_task2_3 AtmajaAIST2023 52 54.927919043886064 ± 0.001367012045991299 55.80 54.00 50.49 53.58 54.34 51.95 71.70 62.74 53.46 50.43 48.06 48.29 63.19 53.81 56.66 48.89 56.25 50.05 50.28 50.63 50.26 51.18 58.63 50.55 51.81 50.79 48.30 49.97
Atmaja_AIST_task2_4 AtmajaAIST2023 50 55.0920471984782 ± 0.0013534875706585426 55.55 54.00 50.32 53.00 54.35 51.84 74.99 64.11 53.39 50.31 48.09 48.29 63.21 54.28 56.55 48.79 56.26 50.16 50.51 50.71 50.01 51.37 58.59 50.87 51.85 50.71 48.06 49.97
Wilkinghoff_FKIE_task2_1 WilkinghoffFKIE2023 5 64.91145175990695 ± 0.0017818544158040373 53.90 50.21 87.14 76.58 63.43 62.21 83.26 74.00 66.06 52.87 67.10 62.11 65.91 50.24 60.66 48.00 58.12 48.37 75.48 51.42 80.22 52.32 82.66 65.21 94.02 72.68 88.98 55.62
Wilkinghoff_FKIE_task2_2 WilkinghoffFKIE2023 18 61.94943271644443 ± 0.0017493450038549405 50.24 50.95 83.54 70.16 58.81 54.89 79.69 68.26 61.27 49.66 68.52 55.97 66.92 50.86 56.70 48.79 59.62 50.11 78.32 56.47 74.26 53.00 86.26 63.26 96.66 81.95 99.10 92.63
Wilkinghoff_FKIE_task2_3 WilkinghoffFKIE2023 9 63.78183448560294 ± 0.0017160757632745873 52.31 50.84 85.86 74.74 61.01 58.47 81.64 71.42 63.95 49.94 68.90 58.07 68.23 51.47 58.02 48.79 59.66 50.11 78.32 56.47 74.48 53.00 86.14 63.26 96.66 81.95 98.92 91.32
Jiang_PSH_task2_1 JiangPSH2023 71 48.91877723956266 ± 0.0013780231177993646 45.49 52.84 46.80 56.05 53.21 51.95 41.25 51.11 48.90 49.46 52.96 50.47 47.59 49.46 54.13 52.52 53.84 49.57 57.68 51.21 86.84 68.84 59.33 53.78 36.75 48.31 45.00 49.94
Jiang_PSH_task2_2 JiangPSH2023 47 55.61393665575548 ± 0.001453889360427255 57.66 50.68 58.27 56.11 48.60 57.05 70.54 66.74 47.05 48.24 63.93 56.18 54.66 49.72 52.97 51.68 55.25 52.42 64.03 51.79 51.17 55.37 78.20 54.00 96.37 83.26 61.39 54.47
Jiang_PSH_task2_3 JiangPSH2023 66 49.99037851318873 ± 0.0015137828936477508 43.59 51.37 46.28 51.47 35.87 48.74 37.22 48.47 52.54 51.60 69.55 63.31 78.29 71.97 53.50 52.42 68.29 54.32 68.09 50.79 71.79 57.95 69.75 50.63 93.30 88.95 66.27 56.32
Wu_qdreamer_task2_1 Wuqdreamer2023 62 51.525660069002065 ± 0.0015822681937240819 44.02 48.21 42.34 49.58 61.71 55.84 60.60 63.68 51.34 48.02 49.74 48.76 54.86 55.59 67.49 49.89 61.95 53.53 74.63 52.11 73.19 63.21 75.79 65.58 83.87 62.53 67.40 57.68
Wu_qdreamer_task2_2 Wuqdreamer2023 37 57.89588861551478 ± 0.0015098156155787597 40.29 48.95 72.82 62.47 70.77 57.47 59.42 63.16 52.56 51.44 64.02 57.79 65.36 57.48 67.49 49.89 61.95 53.53 74.63 52.11 73.19 63.21 75.79 65.58 83.87 62.53 67.40 57.68
Wu_qdreamer_task2_3 Wuqdreamer2023 29 59.262985023209346 ± 0.001379038594802009 45.85 52.53 79.02 60.26 69.46 57.89 56.76 65.26 55.48 50.81 60.25 54.21 69.44 58.87 67.49 49.89 61.95 53.53 74.63 52.11 73.19 63.21 75.79 65.58 83.87 62.53 67.40 57.68
Wu_qdreamer_task2_4 Wuqdreamer2023 36 57.98849302545982 ± 0.0013438879348592308 44.62 52.16 78.25 58.32 53.10 55.26 82.62 65.63 54.05 50.83 58.99 51.20 63.85 53.20 67.49 49.89 61.95 53.53 74.63 52.11 73.19 63.21 75.79 65.58 83.87 62.53 67.40 57.68
Xiao_NJUPT_task2_1 XiaoNJUPT2023 38 57.61233604271262 ± 0.00148382196939156 65.63 50.89 59.59 52.21 68.27 57.68 55.90 63.05 53.97 48.72 58.29 58.16 57.78 50.77 63.22 53.31 62.05 63.24 65.28 56.28 70.36 59.78 74.53 70.82 85.69 70.19 72.85 57.13
Xiao_NJUPT_task2_2 XiaoNJUPT2023 70 49.02196802271064 ± 0.0015200211817074174 43.52 49.79 40.18 50.26 39.96 53.79 39.15 54.58 67.17 51.15 56.16 55.92 62.42 50.61 60.94 53.31 67.42 63.24 63.22 55.32 69.55 60.76 82.87 72.62 87.87 78.84 85.68 71.21
Xiao_NJUPT_task2_2 XiaoNJUPT2023 70 49.02196802271064 ± 0.0015200211817074174 43.52 49.79 40.18 50.26 39.96 53.79 39.15 54.58 67.17 51.15 56.16 55.92 62.42 50.61 68.34 58.69 56.61 50.16 73.39 56.11 82.12 68.11 74.73 57.58 98.63 95.63 88.74 71.37
Jie_IESEFPT_task2_1 JieIESEFPT2023 3 65.62721368076484 ± 0.001765422247029773 55.09 51.26 87.28 74.84 61.63 62.63 94.61 84.79 64.83 53.06 65.56 60.82 64.51 52.91 59.89 47.76 57.62 49.47 74.88 50.23 87.65 60.23 86.15 63.42 96.97 83.66 93.84 73.01
Jie_IESEFPT_task2_2 JieIESEFPT2023 1 66.96865050141963 ± 0.00180162797332972 58.03 51.58 89.03 77.74 60.33 61.53 96.18 85.32 65.66 53.35 66.63 62.45 68.08 55.97 57.68 42.73 56.56 47.47 73.84 51.31 86.96 61.22 82.13 63.43 97.12 82.81 93.38 73.02
Jie_IESEFPT_task2_3 JieIESEFPT2023 25 60.23220801829445 ± 0.001567939212077677 42.57 49.68 63.00 51.89 53.64 53.53 74.61 68.79 73.74 57.25 65.40 62.58 76.04 63.43 61.45 49.00 48.15 47.00 64.40 53.24 73.00 60.26 73.10 56.42 78.00 54.00 53.50 51.00
Jie_IESEFPT_task2_4 JieIESEFPT2023 72 48.705631593217355 ± 0.0014459198323020794 37.04 48.16 70.62 56.16 62.53 54.58 32.52 52.11 55.10 49.65 52.05 51.31 44.95 48.92 57.93 41.74 56.41 47.37 73.88 51.11 86.86 61.32 82.19 63.41 96.79 82.21 93.37 73.03
Gou_UESTC_task2_1 GouUESTC2023 75 47.9520641929154 ± 0.001556273507724516 40.55 50.11 57.13 54.84 43.75 52.32 36.43 49.37 53.23 52.58 54.65 53.63 44.80 52.76 48.96 49.16 49.69 48.05 70.17 55.26 44.24 49.21 72.87 59.44 86.92 75.21 56.00 51.05
Gou_UESTC_task2_2 GouUESTC2023 81 46.15697002269834 ± 0.0015103508446716806 39.40 50.11 57.09 49.16 43.60 50.32 39.18 52.89 45.07 53.35 43.52 49.71 45.70 49.46 48.18 48.63 49.95 51.37 62.73 54.89 54.16 50.11 61.50 51.79 96.32 93.84 50.76 56.16
Gou_UESTC_task2_3 GouUESTC2023 73 48.68995653342131 ± 0.0015180040461601286 42.32 48.47 56.72 50.11 43.96 54.47 41.29 49.42 55.72 52.61 48.24 49.51 51.59 49.14 50.82 51.00 51.48 49.68 54.94 51.26 62.13 49.84 56.42 54.11 72.76 75.63 47.36 52.26
Gou_UESTC_task2_4 GouUESTC2023 82 45.96194603023594 ± 0.0015360163668050005 35.67 49.05 60.98 53.16 35.79 50.00 30.24 49.58 53.57 51.95 59.55 54.79 52.44 49.81 52.72 48.52 59.02 51.63 49.28 49.00 37.62 47.63 67.08 52.00 67.78 59.68 53.64 53.21
Tanaka_GU_task2_1 TanakaGU2023 61 52.545263099486384 ± 0.00162693301788327 41.48 51.00 56.71 54.42 46.13 51.84 62.01 59.95 57.23 52.90 62.11 54.59 48.06 48.49 52.18 48.11 59.00 49.27 63.54 56.11 50.54 54.53 66.36 55.58 95.22 81.16 58.66 54.11
Tanaka_GU_task2_2 TanakaGU2023 63 50.81184160924456 ± 0.0014834146397466558 56.80 52.89 59.46 51.42 49.66 48.32 35.09 48.89 56.19 50.04 55.18 53.12 54.02 50.02 51.34 49.95 55.00 54.37 50.80 49.00 45.18 47.74 53.02 53.74 50.02 50.26 43.70 50.26
Tanaka_GU_task2_3 TanakaGU2023 49 55.25265431943579 ± 0.0013817138477153071 37.89 48.21 60.97 52.74 69.38 59.11 59.42 62.84 52.13 51.25 60.02 55.39 60.33 58.62 56.44 49.58 60.98 50.11 63.36 54.42 47.60 58.32 58.96 51.58 57.50 58.95 47.26 50.11
Tanaka_GU_task2_4 TanakaGU2023 79 46.622594130456804 ± 0.001590474577974257 44.00 50.37 40.00 53.11 45.71 52.05 38.99 50.79 50.63 51.89 57.72 52.17 39.93 50.84 0.00 0.00 48.32 50.32 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 48.06 52.11
Fujimura_NU_task2_1 FujimuraNU2023 54 54.70129260730897 ± 0.0017335695817680035 33.60 49.32 71.36 61.47 57.96 54.47 58.38 61.37 59.03 53.75 61.81 61.08 52.00 59.84 60.70 51.53 61.16 48.58 65.60 56.26 72.32 70.32 82.78 64.26 96.14 80.53 97.62 78.95
Fujimura_NU_task2_2 FujimuraNU2023 58 53.75994905164085 ± 0.0017045574877527835 35.41 49.79 66.51 57.58 54.85 55.32 58.61 59.63 57.20 53.33 59.94 58.84 49.80 58.99 64.32 53.16 62.22 49.05 67.24 54.37 76.08 72.84 77.48 61.74 94.78 73.89 85.40 64.68
Fujimura_NU_task2_3 FujimuraNU2023 55 54.28246173098811 ± 0.0017569003745495227 37.15 49.37 62.91 58.95 50.01 52.68 59.85 58.16 57.95 51.26 57.05 59.10 62.61 60.60 59.74 51.47 53.98 48.42 65.80 54.79 73.04 73.68 82.38 62.89 95.84 80.11 98.16 91.42
Fujimura_NU_task2_4 FujimuraNU2023 59 53.50842811408859 ± 0.0017191745921461637 32.94 49.21 68.89 60.16 52.20 53.00 59.35 59.26 58.14 52.60 60.07 60.22 52.73 59.63 62.42 51.63 62.06 48.79 65.92 54.68 74.50 74.00 81.58 62.68 95.80 79.63 97.94 80.05
Bai_JLESS_task2_1 BaiJLESS2023 12 63.54460439753876 ± 0.0016235543759989214 61.11 51.11 60.54 51.79 63.02 54.63 74.65 62.84 74.22 55.75 64.84 62.19 78.09 63.81 62.47 49.96 53.89 48.16 62.95 51.79 84.85 68.30 75.31 56.21 83.31 55.11 53.97 50.95
Bai_JLESS_task2_2 BaiJLESS2023 13 63.5164873117854 ± 0.0015641551115055045 57.84 51.11 60.98 52.53 67.39 52.89 71.47 62.37 70.61 54.58 66.99 62.57 80.73 67.62 62.47 49.96 53.89 48.16 62.95 51.79 84.85 68.30 75.31 56.21 83.31 55.11 53.97 50.95
Bai_JLESS_task2_3 BaiJLESS2023 6 64.10430038433627 ± 0.0015312095360472697 51.44 50.89 59.85 51.16 70.05 59.58 81.46 69.47 74.51 55.65 67.07 63.03 78.30 63.37 62.47 49.96 53.89 48.16 62.95 51.79 84.85 68.30 75.31 56.21 83.31 55.11 53.97 50.95
Bai_JLESS_task2_4 BaiJLESS2023 22 61.34910760835197 ± 0.0015351699289522023 49.33 52.05 57.54 51.42 60.65 54.05 76.22 66.11 72.02 56.93 63.97 61.06 74.01 64.52 62.47 49.96 53.89 48.16 62.95 51.79 84.85 68.30 75.31 56.21 83.31 55.11 53.97 50.95
Guan_HEU_task2_1 GuanHEU2023 46 55.620217351968016 ± 0.001600989251423758 55.70 50.84 59.87 55.05 61.15 57.05 73.41 72.58 55.41 49.71 51.94 50.60 45.28 48.76 56.15 52.63 58.25 50.63 58.03 50.95 61.49 48.53 73.71 50.32 87.26 65.11 90.52 62.79
Guan_HEU_task2_2 GuanHEU2023 16 62.408172184960776 ± 0.0016644393094324126 55.53 50.74 64.33 54.16 62.60 57.47 82.75 75.84 57.83 50.51 61.75 54.98 80.14 68.50 60.42 49.37 51.92 49.11 65.05 52.21 67.00 57.63 83.18 61.47 92.52 71.58 92.33 63.21
Guan_HEU_task2_3 GuanHEU2023 40 57.26749679751192 ± 0.0016441315830157254 51.06 53.37 68.87 55.84 62.37 57.84 55.20 54.89 55.39 50.32 60.60 50.76 67.31 50.89 60.63 52.53 57.25 50.37 67.02 52.37 57.62 52.53 58.66 52.05 79.35 59.42 56.24 48.47
Guan_HEU_task2_4 GuanHEU2023 14 63.50321347349609 ± 0.0016921801501565013 62.93 52.05 68.94 54.21 66.41 60.63 79.47 72.47 57.22 50.76 62.38 54.96 78.46 61.47 63.04 50.21 56.96 48.95 67.71 54.84 66.97 56.05 79.49 60.58 91.91 71.05 89.35 60.05
Hauser_JKU_task2_1 HauserJKU2023 86 41.40741259250251 ± 0.001374452454520565 40.70 48.47 36.58 48.74 37.85 50.32 25.95 47.89 52.84 51.26 41.91 49.08 44.11 48.23 46.18 48.91 49.33 49.53 40.02 49.34 48.18 58.11 43.10 49.76 52.08 51.57 64.38 58.85
LEE_KNU_task2_1 LEEKNU2023 85 43.73815668367107 ± 0.0014042933269652487 39.70 50.05 43.19 52.05 37.21 51.32 33.75 50.42 43.11 47.37 46.73 48.48 48.24 51.13 45.50 54.57 46.00 49.37 73.40 59.73 65.52 48.16 77.56 54.53 83.38 62.89 99.27 98.74
LEE_KNU_task2_2 LEEKNU2023 84 44.231914616941665 ± 0.00130457675996216 40.03 50.21 42.70 51.58 38.82 51.68 35.20 49.53 43.53 47.37 46.42 48.50 49.01 52.08 46.38 51.47 47.74 48.27 70.84 50.58 65.31 52.16 78.20 51.58 82.07 51.90 97.06 97.57
LEE_KNU_task2_3 LEEKNU2023 88 40.80929524258176 ± 0.001304646555059204 39.46 48.79 44.09 51.79 34.09 49.74 27.97 48.26 49.86 49.92 35.16 48.63 40.12 49.26 42.38 56.58 49.22 42.92 62.94 57.58 47.16 48.89 65.95 58.42 83.38 63.48 97.06 98.74
LEE_KNU_task2_4 LEEKNU2023 87 41.253746415955696 ± 0.0013222783593330345 42.82 49.37 44.13 49.89 34.50 50.89 25.97 47.95 49.55 49.63 35.85 48.59 44.59 51.27 42.92 55.84 51.34 49.05 62.10 57.63 46.38 48.73 68.30 57.10 80.14 63.10 96.92 96.37
QianXuHu_BITNUDT_task2_1 QianXuHuBITNUDT2023 39 57.470075856395965 ± 0.001575522945532246 60.59 51.37 76.90 58.32 58.39 62.16 69.83 62.79 54.82 52.47 42.76 47.37 61.34 53.08 66.33 49.68 63.35 51.26 71.59 58.00 71.94 59.42 71.77 59.84 78.24 64.11 43.11 49.05
QianXuHu_BITNUDT_task2_2 QianXuHuBITNUDT2023 42 56.31700501343051 ± 0.0017126948526507567 60.59 51.37 76.90 58.32 60.31 54.68 58.46 59.79 54.82 52.47 42.76 47.37 61.34 53.08 66.33 49.68 63.35 51.26 71.59 58.00 71.94 59.42 71.77 59.84 78.24 64.11 43.11 49.05
QianXuHu_BITNUDT_task2_3 QianXuHuBITNUDT2023 31 59.06204701591861 ± 0.0015102887361449933 57.76 53.00 46.69 51.53 64.75 59.42 72.73 62.58 63.37 53.03 57.77 59.02 69.93 55.41 59.69 51.16 60.55 48.84 59.66 51.21 71.96 64.32 73.46 58.89 78.89 59.42 65.05 55.00
QianXuHu_BITNUDT_task2_4 QianXuHuBITNUDT2023 60 53.39003048197518 ± 0.0014644056967616462 57.76 53.00 46.69 51.53 41.83 52.16 47.12 51.16 63.37 53.03 57.77 59.02 69.93 55.41 59.69 51.16 60.55 48.84 59.66 51.21 71.96 64.32 73.46 58.89 78.89 59.42 65.05 55.00


Supplementary metrics (recall, precision, and F1 score)

Rank Submission Information Evaluation Dataset
Submission Code Technical
Report 		Official
Rank 		ToyDrone
(F1 score) 		ToyDrone
(Recall) 		ToyDrone
(Precision) 		ToyNscale
(F1 score) 		ToyNscale
(Recall) 		ToyNscale
(Precision) 		ToyTank
(F1 score) 		ToyTank
(Recall) 		ToyTank
(Precision) 		Vacuum
(F1 score) 		Vacuum
(Recall) 		Vacuum
(Precision) 		Bandsaw
(F1 score) 		Bandsaw
(Recall) 		Bandsaw
(Precision) 		Grinder
(F1 score) 		Grinder
(Recall) 		Grinder
(Precision) 		Shaker
(F1 score) 		Shaker
(Recall) 		Shaker
(Precision)
DCASE2023_baseline_task2_MAHALA DCASE2023baseline2023 24 15.56 8.89 62.50 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 53.38 100.00 36.41 43.65 100.00 27.92 66.06 100.00 49.32
DCASE2023_baseline_task2_MSE DCASE2023baseline2023 30 61.86 62.98 60.77 63.20 78.20 53.03 64.38 72.66 57.79 67.07 71.79 62.92 52.64 71.39 41.69 47.10 68.28 35.95 62.82 76.57 53.26
Du_NERCSLIP_task2_1 DuNERCSLIP2023 21 61.08 60.98 61.18 75.34 74.72 75.96 56.03 55.93 56.13 75.96 75.16 76.77 46.47 49.03 44.16 36.76 52.06 28.41 40.53 40.70 40.36
Du_NERCSLIP_task2_2 DuNERCSLIP2023 19 60.13 59.93 60.34 73.90 73.25 74.56 58.08 57.72 58.45 79.08 78.38 79.79 46.99 47.88 46.13 33.33 47.06 25.81 83.70 83.52 83.88
Du_NERCSLIP_task2_3 DuNERCSLIP2023 20 60.00 60.00 60.00 74.71 73.85 75.59 59.07 58.98 59.16 76.04 75.16 76.94 50.85 53.10 48.78 36.65 50.91 28.63 82.57 82.22 82.92
Du_NERCSLIP_task2_4 DuNERCSLIP2023 23 59.06 58.98 59.14 74.01 72.87 75.19 59.05 58.98 59.12 75.05 74.35 75.76 48.29 52.01 45.06 38.22 52.63 30.00 82.75 82.22 83.29
He_XJU_task2_1 HeXJU2023 78 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
He_XJU_task2_2 HeXJU2023 83 12.14 7.69 28.74 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
He_XJU_task2_3 HeXJU2023 80 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
He_XJU_task2_4 HeXJU2023 74 21.65 14.81 40.16 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
Lv_HUAKONG_task2_1 LvHUAKONG2023 11 42.30 37.53 48.45 69.05 68.87 69.23 58.97 58.85 59.09 78.58 78.68 78.48 43.31 50.96 37.66 49.84 68.28 39.24 65.17 64.91 65.42
Lv_HUAKONG_task2_2 LvHUAKONG2023 15 48.41 45.71 51.45 64.80 64.86 64.74 55.85 54.88 56.85 71.88 71.34 72.43 43.95 50.83 38.72 50.10 67.74 39.75 68.34 68.69 68.00
Lv_HUAKONG_task2_3 LvHUAKONG2023 8 41.12 35.20 49.44 71.86 71.50 72.22 63.06 62.22 63.93 79.44 79.20 79.68 48.08 55.60 42.35 52.00 71.98 40.70 68.34 68.69 68.00
Lv_HUAKONG_task2_4 LvHUAKONG2023 2 50.70 50.21 51.20 77.54 77.54 77.54 66.34 66.27 66.41 87.74 87.82 87.66 48.30 57.14 41.83 48.41 66.67 38.00 66.92 66.45 67.40
Jiang_THUEE_task2_1 JiangTHUEE2023 4 59.54 55.73 63.91 66.40 63.24 69.90 58.73 51.10 69.05 71.19 66.44 76.67 59.96 71.39 51.68 45.44 63.15 35.49 65.28 65.57 64.98
Jiang_THUEE_task2_2 JiangTHUEE2023 35 19.30 11.29 66.21 56.70 49.65 66.08 52.34 42.71 67.56 65.01 56.81 75.97 55.39 62.92 49.47 48.52 66.30 38.26 62.65 59.04 66.74
Jiang_THUEE_task2_3 JiangTHUEE2023 7 54.23 53.93 54.53 70.95 70.00 71.92 67.92 65.88 70.09 70.74 64.44 78.40 54.90 63.96 48.09 52.46 71.27 41.51 68.32 67.73 68.93
Jiang_THUEE_task2_4 JiangTHUEE2023 17 53.09 53.53 52.67 64.33 62.40 66.38 59.70 54.19 66.46 68.47 62.20 76.14 49.55 57.28 43.66 52.41 71.27 41.45 68.32 67.73 68.93
JiaJun_HFUU_task2_1 JiaJunHFUU2023 33 0.00 0.00 0.00 38.52 25.08 83.01 0.00 0.00 0.00 38.71 24.00 100.00 44.28 32.26 70.59 39.77 32.23 51.92 24.91 16.85 47.78
JiaJun_HFUU_task2_2 JiaJunHFUU2023 33 0.00 0.00 0.00 38.52 25.08 83.01 0.00 0.00 0.00 38.71 24.00 100.00 44.28 32.26 70.59 39.77 32.23 51.92 24.91 16.85 47.78
JiaJun_HFUU_task2_3 JiaJunHFUU2023 27 11.80 6.55 60.00 38.52 25.08 83.01 0.00 0.00 0.00 38.71 24.00 100.00 44.28 32.26 70.59 39.77 32.23 51.92 24.91 16.85 47.78
JiaJun_HFUU_task2_4 JiaJunHFUU2023 41 0.00 0.00 0.00 38.52 25.08 83.01 0.00 0.00 0.00 38.71 24.00 100.00 20.38 14.16 36.36 39.77 32.23 51.92 24.91 16.85 47.78
Zhang_DKU_task2_1 ZhangDKU2023 76 0.00 0.00 0.00 0.00 0.00 0.00 12.29 6.77 66.67 0.00 0.00 0.00 7.32 3.92 54.55 16.33 9.80 48.78 6.41 3.36 70.00
Zhang_DKU_task2_2 ZhangDKU2023 57 0.00 0.00 0.00 7.47 3.89 92.50 0.00 0.00 0.00 0.00 0.00 0.00 35.79 28.64 47.71 10.26 5.80 44.44 12.96 7.44 50.00
Zhang_DKU_task2_3 ZhangDKU2023 65 0.00 0.00 0.00 0.00 0.00 0.00 6.41 3.33 83.33 0.00 0.00 0.00 37.38 30.08 49.38 0.00 0.00 0.00 37.46 29.70 50.72
Zhang_DKU_task2_4 ZhangDKU2023 76 0.00 0.00 0.00 0.00 0.00 0.00 12.29 6.77 66.67 0.00 0.00 0.00 7.32 3.92 54.55 16.33 9.80 48.78 6.41 3.36 70.00
Zhou_SHNU_task2_1 ZhouSHNU2023 32 53.00 50.98 55.18 47.78 36.24 70.09 28.32 20.21 47.29 46.72 35.10 69.85 54.93 56.48 53.46 50.10 54.24 46.56 57.52 51.28 65.49
Zhou_SHNU_task2_2 ZhouSHNU2023 69 53.00 50.98 55.18 47.78 36.24 70.09 28.32 20.21 47.29 46.72 35.10 69.85 19.47 13.48 35.01 32.17 51.51 23.39 21.36 13.48 51.44
Zhou_SHNU_task2_3 ZhouSHNU2023 10 41.16 31.49 59.39 49.26 42.42 58.73 58.23 51.31 67.31 62.19 50.51 80.90 54.93 56.48 53.46 50.10 54.24 46.56 57.52 51.28 65.49
Zhou_SHNU_task2_1 ZhouSHNU2023 32 53.00 50.98 55.18 47.78 36.24 70.09 28.32 20.21 47.29 46.72 35.10 69.85 54.93 56.48 53.46 50.10 54.24 46.56 57.52 51.28 65.49
Zhang_BIT_task2_1 ZhangBIT2023 28 53.82 46.34 64.18 56.96 56.28 57.67 57.38 57.38 57.38 32.27 21.28 66.67 52.75 63.06 45.34 45.51 63.15 35.57 59.37 60.38 58.38
Zhang_BIT_task2_2 ZhangBIT2023 56 7.40 3.92 66.22 52.53 52.53 52.53 34.80 24.30 61.27 0.00 0.00 0.00 58.43 70.59 49.85 45.86 63.16 36.00 63.25 62.88 63.61
Zhang_BIT_task2_3 ZhangBIT2023 67 46.93 46.81 47.05 49.88 49.68 50.08 51.00 50.98 51.02 48.85 48.82 48.88 44.12 52.17 38.22 42.60 59.63 33.14 50.08 50.57 49.60
Zhang_BIT_task2_4 ZhangBIT2023 43 49.24 41.75 60.01 67.14 65.79 68.55 60.89 60.59 61.19 35.38 24.50 63.64 43.68 52.00 37.66 38.67 54.15 30.07 54.99 54.60 55.38
Liu_CQUPT_task2_1 LiuCQUPT2023 44 48.11 47.12 49.14 54.62 51.53 58.10 23.97 14.79 63.12 19.19 11.27 64.79 47.50 55.47 41.53 52.73 71.79 41.67 58.26 58.39 58.14
Liu_CQUPT_task2_2 LiuCQUPT2023 64 48.11 47.12 49.14 54.62 51.53 58.10 23.97 14.79 63.12 19.19 11.27 64.79 47.50 55.47 41.53 52.73 71.79 41.67 58.26 58.39 58.14
Liu_CQUPT_task2_3 LiuCQUPT2023 48 48.11 47.12 49.14 54.62 51.53 58.10 23.97 14.79 63.12 19.19 11.27 64.79 47.50 55.47 41.53 52.73 71.79 41.67 58.26 58.39 58.14
Liu_CQUPT_task2_4 LiuCQUPT2023 45 48.11 47.12 49.14 54.62 51.53 58.10 23.97 14.79 63.12 19.19 11.27 64.79 47.50 55.47 41.53 52.73 71.79 41.67 58.26 58.39 58.14
Atmaja_AIST_task2_1 AtmajaAIST2023 53 22.33 14.12 53.33 61.67 71.74 54.09 45.74 40.19 53.07 70.98 77.97 65.14 38.61 40.22 37.11 38.86 48.69 32.34 60.01 67.09 54.29
Atmaja_AIST_task2_2 AtmajaAIST2023 51 22.02 14.17 49.40 61.84 76.80 51.75 49.66 44.61 56.00 71.25 75.95 67.09 0.00 0.00 0.00 39.16 49.12 32.56 59.80 67.39 53.74
Atmaja_AIST_task2_3 AtmajaAIST2023 52 22.02 14.12 50.00 62.22 73.85 53.75 47.13 41.73 54.13 70.95 75.95 66.58 38.61 40.22 37.11 38.54 48.69 31.89 60.01 63.21 57.11
Atmaja_AIST_task2_4 AtmajaAIST2023 50 0.00 0.00 0.00 62.42 73.85 54.05 0.00 0.00 0.00 67.57 100.00 51.02 38.61 40.22 37.11 38.46 47.21 32.44 58.72 62.47 55.40
Wilkinghoff_FKIE_task2_1 WilkinghoffFKIE2023 5 67.21 78.91 58.53 72.90 75.00 70.92 61.93 70.13 55.45 73.22 91.30 61.12 54.42 54.79 54.05 50.00 56.14 45.07 59.34 54.55 65.06
Wilkinghoff_FKIE_task2_2 WilkinghoffFKIE2023 18 59.68 61.09 58.33 70.42 71.74 69.15 63.29 66.67 60.24 76.43 94.74 64.06 25.88 19.05 40.34 31.62 24.24 45.45 39.94 30.83 56.66
Wilkinghoff_FKIE_task2_3 WilkinghoffFKIE2023 9 63.18 69.62 57.84 75.76 78.05 73.60 63.88 71.79 57.54 75.73 96.91 62.15 37.90 31.58 47.40 41.10 38.10 44.61 49.54 43.49 57.56
Jiang_PSH_task2_1 JiangPSH2023 71 66.67 100.00 50.00 59.26 71.79 50.45 63.33 79.20 52.76 45.00 40.73 50.27 53.38 100.00 36.41 44.01 100.00 28.21 66.05 97.97 49.81
Jiang_PSH_task2_2 JiangPSH2023 47 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
Jiang_PSH_task2_3 JiangPSH2023 66 0.00 0.00 0.00 53.90 52.41 55.47 13.80 7.69 67.11 13.79 7.69 66.67 51.53 61.74 44.21 56.97 75.31 45.81 69.39 68.69 70.10
Wu_qdreamer_task2_1 Wuqdreamer2023 62 58.68 63.77 54.35 27.76 18.95 51.87 41.31 30.00 66.30 73.53 100.00 58.14 10.76 6.70 27.27 7.08 4.76 13.79 43.64 33.27 63.38
Wu_qdreamer_task2_2 Wuqdreamer2023 37 57.86 63.01 53.49 69.75 98.99 53.85 65.20 81.67 54.26 73.68 98.99 58.68 33.73 29.45 39.47 43.69 38.96 49.72 62.67 74.68 53.99
Wu_qdreamer_task2_3 Wuqdreamer2023 29 6.77 3.91 25.21 71.57 94.74 57.51 66.37 85.06 54.41 0.00 0.00 0.00 54.22 78.26 41.47 45.82 68.29 34.47 62.74 75.67 53.58
Wu_qdreamer_task2_4 Wuqdreamer2023 36 12.48 7.67 33.58 72.81 95.83 58.70 7.22 3.85 57.78 76.86 94.91 64.58 52.32 76.88 39.66 44.09 60.68 34.62 28.04 18.55 57.46
Xiao_NJUPT_task2_1 XiaoNJUPT2023 38 66.52 83.81 55.14 66.59 82.29 55.92 65.24 63.82 66.73 46.22 35.51 66.19 42.22 50.41 36.32 44.72 83.99 30.47 64.78 85.92 51.99
Xiao_NJUPT_task2_2 XiaoNJUPT2023 70 0.00 0.00 0.00 51.17 48.63 53.98 0.00 0.00 0.00 0.00 0.00 0.00 59.68 71.34 51.30 39.84 55.63 31.03 58.85 59.25 58.45
Xiao_NJUPT_task2_2 XiaoNJUPT2023 70 0.00 0.00 0.00 51.17 48.63 53.98 0.00 0.00 0.00 0.00 0.00 0.00 59.68 71.34 51.30 39.84 55.63 31.03 58.85 59.25 58.45
Jie_IESEFPT_task2_1 JieIESEFPT2023 3 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 53.38 100.00 36.41 43.65 100.00 27.92 66.06 100.00 49.32
Jie_IESEFPT_task2_2 JieIESEFPT2023 1 69.48 85.61 58.46 78.79 85.06 73.38 61.71 70.13 55.10 80.32 100.00 67.11 53.93 55.60 52.36 48.48 52.58 44.98 67.39 74.55 61.48
Jie_IESEFPT_task2_3 JieIESEFPT2023 25 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 0.00 0.00 0.00 53.38 100.00 36.41 43.65 100.00 27.92 66.06 100.00 49.32
Jie_IESEFPT_task2_4 JieIESEFPT2023 72 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 0.00 0.00 0.00 53.38 100.00 36.41 43.65 100.00 27.92 66.06 100.00 49.32
Gou_UESTC_task2_1 GouUESTC2023 75 0.00 0.00 0.00 50.61 49.26 52.03 0.00 0.00 0.00 0.00 0.00 0.00 11.65 6.45 60.00 42.73 96.48 27.44 56.47 71.01 46.87
Gou_UESTC_task2_2 GouUESTC2023 81 49.33 39.71 65.12 57.92 57.38 58.47 43.90 32.73 66.67 13.75 7.68 65.75 35.14 40.13 31.25 30.57 42.11 24.00 46.43 46.92 45.96
Gou_UESTC_task2_3 GouUESTC2023 73 13.78 7.69 66.67 55.56 55.71 55.40 44.83 34.87 62.77 13.53 7.68 56.80 48.43 57.67 41.75 38.22 52.63 30.00 50.32 50.57 50.08
Gou_UESTC_task2_4 GouUESTC2023 82 0.00 0.00 0.00 50.61 49.26 52.03 0.00 0.00 0.00 0.00 0.00 0.00 11.65 6.45 60.00 42.73 96.48 27.44 56.47 71.01 46.87
Tanaka_GU_task2_1 TanakaGU2023 61 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 42.55 41.10 44.12 41.12 44.18 38.46 66.06 100.00 49.32
Tanaka_GU_task2_2 TanakaGU2023 63 58.63 64.98 53.41 5.74 3.00 66.67 0.00 0.00 0.00 6.87 3.84 32.43 52.46 86.83 37.58 0.00 0.00 0.00 59.13 73.56 49.43
Tanaka_GU_task2_3 TanakaGU2023 49 7.27 3.91 51.43 53.45 45.04 65.73 62.50 62.60 62.41 31.17 21.43 57.14 41.44 46.68 37.26 40.29 49.12 34.15 46.54 39.18 57.31
Tanaka_GU_task2_4 TanakaGU2023 79 0.00 0.00 0.00 37.18 36.32 38.08 26.75 18.00 52.02 13.49 7.66 56.43 44.30 53.20 37.95 38.85 47.21 33.00 31.68 29.38 34.38
Fujimura_NU_task2_1 FujimuraNU2023 54 19.01 11.29 60.00 61.64 52.94 73.77 46.69 35.51 68.15 41.09 30.21 64.19 55.88 63.96 49.61 47.24 64.21 37.36 53.66 53.15 54.18
Fujimura_NU_task2_2 FujimuraNU2023 58 23.53 14.77 57.83 58.23 49.65 70.39 44.16 32.98 66.81 49.33 40.34 63.45 55.70 61.67 50.78 49.39 66.85 39.16 48.55 48.26 48.85
Fujimura_NU_task2_3 FujimuraNU2023 55 13.56 7.69 57.48 55.29 50.75 60.71 7.28 3.92 50.51 48.24 38.40 64.86 49.70 58.74 43.08 41.78 57.93 32.67 52.75 53.34 52.17
Fujimura_NU_task2_4 FujimuraNU2023 59 13.56 7.69 57.48 57.48 49.94 67.71 32.21 21.38 65.26 44.36 33.22 66.76 54.59 62.07 48.71 44.69 61.26 35.17 50.55 50.28 50.81
Bai_JLESS_task2_1 BaiJLESS2023 12 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
Bai_JLESS_task2_2 BaiJLESS2023 13 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
Bai_JLESS_task2_3 BaiJLESS2023 6 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
Bai_JLESS_task2_4 BaiJLESS2023 22 0.00 0.00 0.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 53.38 100.00 36.41 43.65 100.00 27.92 66.06 100.00 49.32
Guan_HEU_task2_1 GuanHEU2023 46 51.76 43.92 62.99 54.10 49.26 60.00 51.38 42.00 66.14 51.53 37.33 83.17 43.75 46.45 41.33 38.07 49.06 31.10 42.60 39.18 46.68
Guan_HEU_task2_2 GuanHEU2023 16 50.24 42.00 62.50 51.03 42.31 64.28 56.52 46.34 72.41 55.48 40.14 89.80 36.59 38.42 34.91 44.42 50.91 39.40 68.09 59.23 80.07
Guan_HEU_task2_3 GuanHEU2023 40 26.27 18.04 48.32 59.90 55.08 65.65 57.73 54.11 61.87 38.75 28.69 59.68 50.87 58.74 44.85 47.42 57.26 40.46 64.86 62.97 66.87
Guan_HEU_task2_4 GuanHEU2023 14 52.84 46.47 61.25 59.04 53.33 66.12 55.85 45.38 72.60 63.84 50.03 88.17 38.77 39.69 37.89 45.09 50.72 40.58 69.96 63.55 77.80
Hauser_JKU_task2_1 HauserJKU2023 86 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 53.38 100.00 36.41 43.65 100.00 27.92 66.06 100.00 49.32
LEE_KNU_task2_1 LEEKNU2023 85 29.85 21.18 50.56 40.28 37.30 43.78 7.13 3.92 39.83 0.00 0.00 0.00 39.34 46.68 34.00 28.50 38.10 22.77 48.13 48.26 48.00
LEE_KNU_task2_2 LEEKNU2023 84 62.39 80.95 50.75 59.60 72.00 50.85 59.41 75.00 49.18 64.14 86.36 51.01 50.49 68.29 40.05 42.64 75.36 29.73 56.47 64.51 50.21
LEE_KNU_task2_3 LEEKNU2023 88 41.50 32.45 57.53 40.66 37.30 44.69 0.00 0.00 0.00 7.40 3.92 66.22 45.16 53.50 39.07 31.87 44.90 24.70 42.93 43.01 42.85
LEE_KNU_task2_4 LEEKNU2023 87 59.89 71.79 51.38 57.45 67.83 49.82 63.93 82.35 52.24 68.12 87.64 55.71 45.53 64.97 35.04 45.16 73.68 32.56 56.90 66.67 49.62
QianXuHu_BITNUDT_task2_1 QianXuHuBITNUDT2023 39 0.00 0.00 0.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 53.56 100.00 36.58 43.65 100.00 27.92 68.79 98.08 52.98
QianXuHu_BITNUDT_task2_2 QianXuHuBITNUDT2023 42 0.00 0.00 0.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 53.56 100.00 36.58 43.65 100.00 27.92 68.79 98.08 52.98
QianXuHu_BITNUDT_task2_3 QianXuHuBITNUDT2023 31 0.00 0.00 0.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 53.56 100.00 36.58 43.65 100.00 27.92 68.79 98.08 52.98
QianXuHu_BITNUDT_task2_4 QianXuHuBITNUDT2023 60 0.00 0.00 0.00 66.67 100.00 50.00 66.67 100.00 50.00 66.67 100.00 50.00 53.56 100.00 36.58 43.65 100.00 27.92 68.79 98.08 52.98


Domain-wise performance

Rank Submission Information Ranking Eveluation Dataset in Source Domain Eveluation Dataset in Target Domain
Submission Code Technical
Report 		Official
Rank 		Official
Score 		Harmonic mean
(AUC, source) 		ToyDrone
(AUC, source) 		ToyDrone
(pAUC, source) 		ToyNscale
(AUC, source) 		ToyNscale
(pAUC, source) 		ToyTank
(AUC, source) 		ToyTank
(pAUC, source) 		Vacuum
(AUC, source) 		Vacuum
(pAUC, source) 		Bandsaw
(AUC, source) 		Bandsaw
(pAUC, source) 		Grinder
(AUC, source) 		Grinder
(pAUC, source) 		Shaker
(AUC, source) 		Shaker
(pAUC, source) 		Harmonic mean
(AUC, target) 		ToyDrone
(AUC, target) 		ToyDrone
(pAUC, target) 		ToyNscale
(AUC, target) 		ToyNscale
(pAUC, target) 		ToyTank
(AUC, target) 		ToyTank
(pAUC, target) 		Vacuum
(AUC, target) 		Vacuum
(pAUC, target) 		Bandsaw
(AUC, target) 		Bandsaw
(pAUC, target) 		Grinder
(AUC, target) 		Grinder
(pAUC, target) 		Shaker
(AUC, target) 		Shaker
(pAUC, target)
DCASE2023_baseline_task2_MAHALA DCASE2023baseline2023 24 61.051 78.71 81.30 51.42 66.78 50.89 80.12 53.84 83.84 65.32 83.64 57.54 74.09 59.55 84.77 62.33 53.09 46.22 51.42 40.90 50.89 45.32 53.84 90.06 65.32 58.86 57.54 50.68 59.55 63.00 62.33
DCASE2023_baseline_task2_MSE DCASE2023baseline2023 30 59.255 74.23 79.68 53.68 77.00 51.79 72.12 58.26 88.16 59.47 66.67 50.91 70.68 58.46 69.43 54.92 52.54 56.10 53.68 47.16 51.79 64.68 58.26 45.32 59.47 48.29 50.91 55.17 58.46 56.04 54.92
Du_NERCSLIP_task2_1 DuNERCSLIP2023 21 61.403 72.34 70.84 51.11 83.28 64.84 65.98 56.63 90.56 62.11 72.68 49.37 50.30 49.40 92.56 82.87 56.49 49.00 51.11 89.26 64.84 56.62 56.63 76.36 62.11 34.77 49.37 44.69 49.40 95.96 82.87
Du_NERCSLIP_task2_2 DuNERCSLIP2023 19 61.765 73.01 70.98 51.47 83.94 65.37 66.36 57.58 90.48 60.84 73.28 49.92 52.06 49.21 91.73 80.78 56.98 49.12 51.47 89.94 65.37 56.94 57.58 75.06 60.84 35.23 49.92 46.39 49.21 94.79 80.78
Du_NERCSLIP_task2_3 DuNERCSLIP2023 20 61.727 72.81 71.06 52.05 83.10 65.05 66.28 58.00 89.28 60.16 72.21 50.54 53.24 48.11 89.96 76.08 57.42 49.30 52.05 89.92 65.05 57.44 58.00 73.66 60.16 35.89 50.54 48.05 48.11 92.25 76.08
Du_NERCSLIP_task2_4 DuNERCSLIP2023 23 61.333 71.40 69.00 52.16 82.06 64.00 64.14 58.74 88.24 59.74 69.97 51.17 53.25 47.75 88.02 69.74 57.86 50.74 52.16 89.84 64.00 58.22 58.74 72.74 59.74 36.44 51.17 48.93 47.75 88.29 69.74
He_XJU_task2_1 HeXJU2023 78 46.892 58.64 75.12 49.21 67.44 52.74 58.18 50.16 73.58 51.00 37.58 47.96 57.63 50.84 60.61 49.64 37.04 26.76 49.21 41.40 52.74 48.42 50.16 26.10 51.00 45.66 47.96 49.37 50.84 38.00 49.64
He_XJU_task2_2 HeXJU2023 83 44.809 55.40 62.58 50.00 63.21 50.89 56.30 51.21 67.96 47.95 42.08 48.28 48.16 52.09 56.98 48.85 34.67 27.84 50.00 35.42 50.89 42.68 51.21 17.28 47.95 56.67 48.28 54.92 52.09 48.60 48.85
He_XJU_task2_3 HeXJU2023 80 46.411 55.14 67.16 49.74 52.54 47.58 39.56 52.11 74.86 53.32 47.19 51.60 54.99 53.13 66.58 57.94 36.65 29.58 49.74 21.06 47.58 66.34 52.11 27.70 53.32 45.41 51.60 44.79 53.13 70.51 57.94
He_XJU_task2_4 HeXJU2023 74 48.179 51.28 72.78 50.11 57.84 52.74 65.20 50.37 36.20 52.53 35.60 49.55 68.39 58.46 50.52 49.51 42.66 26.88 50.11 46.88 52.74 37.16 50.37 72.74 52.53 37.83 49.55 63.50 58.46 44.05 49.51
Lv_HUAKONG_task2_1 LvHUAKONG2023 11 63.641 67.89 50.08 49.47 80.50 56.95 72.54 62.79 88.18 70.32 55.63 51.15 69.70 62.16 75.32 65.50 64.79 55.96 49.47 70.10 56.95 64.68 62.79 82.94 70.32 52.92 51.15 64.38 62.16 71.68 65.50
Lv_HUAKONG_task2_2 LvHUAKONG2023 15 62.912 68.55 54.44 49.32 74.78 52.21 71.50 62.79 78.78 63.95 59.17 51.76 70.62 63.44 79.18 71.23 62.74 50.80 49.32 63.20 52.21 59.44 62.79 79.74 63.95 54.75 51.76 67.01 63.44 74.01 71.23
Lv_HUAKONG_task2_3 LvHUAKONG2023 8 63.858 70.72 49.12 49.84 81.22 56.79 79.82 58.21 84.28 70.32 64.57 50.11 73.13 61.98 78.40 63.13 64.30 58.44 49.84 74.18 56.79 56.76 58.21 85.66 70.32 49.98 50.11 67.15 61.98 71.00 63.13
Lv_HUAKONG_task2_4 LvHUAKONG2023 2 66.386 72.18 59.60 49.37 81.08 57.00 75.62 63.79 96.82 87.42 58.31 50.30 71.01 61.22 76.42 65.24 68.03 50.78 49.37 84.40 57.00 74.00 63.79 90.70 87.42 58.65 50.30 62.87 61.22 72.18 65.24
Jiang_THUEE_task2_1 JiangTHUEE2023 4 65.403 82.43 85.88 49.74 82.90 61.63 87.12 59.74 98.74 76.42 80.56 56.64 69.54 62.41 78.05 64.68 57.91 41.36 49.74 65.92 61.63 49.38 59.74 70.08 76.42 63.63 56.64 56.24 62.41 74.05 64.68
Jiang_THUEE_task2_2 JiangTHUEE2023 35 58.136 86.38 89.40 49.11 88.36 55.42 90.72 54.37 99.50 71.37 80.72 51.12 73.88 61.40 86.68 65.33 44.24 21.24 49.11 57.34 55.42 44.64 54.37 64.36 71.37 47.95 51.12 55.02 61.40 59.79 65.33
Jiang_THUEE_task2_3 JiangTHUEE2023 7 63.897 82.17 78.64 48.89 84.20 52.53 87.92 55.89 99.28 73.00 74.63 50.75 73.24 61.77 82.64 64.50 57.86 36.26 48.89 72.06 52.53 57.42 55.89 69.66 73.00 60.02 50.75 60.14 61.77 69.13 64.50
Jiang_THUEE_task2_4 JiangTHUEE2023 17 62.381 79.16 67.80 49.79 85.00 53.16 86.42 55.42 97.74 65.26 70.86 50.98 71.86 63.08 82.73 65.23 55.93 41.60 49.79 61.16 53.16 48.42 55.42 63.88 65.26 58.20 50.98 59.36 63.08 69.33 65.23
JiaJun_HFUU_task2_1 JiaJunHFUU2023 33 58.170 80.83 89.98 49.32 91.04 64.53 90.14 55.63 99.58 73.95 82.62 57.83 66.50 55.84 61.64 49.32 46.16 23.28 49.32 77.28 64.53 38.08 55.63 66.00 73.95 62.63 57.83 53.07 55.84 51.17 49.32
JiaJun_HFUU_task2_2 JiaJunHFUU2023 33 58.170 80.83 89.98 49.32 91.04 64.53 90.14 55.63 99.58 73.95 82.62 57.83 66.50 55.84 61.64 49.32 46.16 23.28 49.32 77.28 64.53 38.08 55.63 66.00 73.95 62.63 57.83 53.07 55.84 51.17 49.32
JiaJun_HFUU_task2_3 JiaJunHFUU2023 27 59.539 80.07 83.74 48.79 91.04 64.53 90.14 55.63 99.58 73.95 82.62 57.83 66.50 55.84 61.64 49.32 49.19 29.76 48.79 77.28 64.53 38.08 55.63 66.00 73.95 62.63 57.83 53.07 55.84 51.17 49.32
JiaJun_HFUU_task2_4 JiaJunHFUU2023 41 56.940 79.07 89.98 49.32 91.04 64.53 90.14 55.63 99.58 73.95 71.25 50.64 66.50 55.84 61.64 49.32 45.14 23.28 49.32 77.28 64.53 38.08 55.63 66.00 73.95 51.60 50.64 53.07 55.84 51.17 49.32
Zhang_DKU_task2_1 ZhangDKU2023 76 47.856 63.43 64.16 49.63 64.30 51.42 64.94 51.84 66.34 49.68 71.17 50.77 54.60 53.80 61.06 50.38 36.59 34.52 49.63 47.90 51.42 39.12 51.84 25.70 49.68 35.34 50.77 54.97 53.80 32.77 50.38
Zhang_DKU_task2_2 ZhangDKU2023 57 53.943 68.29 69.58 52.37 65.06 64.11 81.22 52.68 82.12 56.00 67.37 55.05 67.70 57.10 53.62 50.72 43.79 50.18 52.37 89.24 64.11 24.24 52.68 29.76 56.00 47.08 55.05 59.02 57.10 63.71 50.72
Zhang_DKU_task2_3 ZhangDKU2023 65 50.362 62.37 52.94 47.74 57.34 54.11 64.58 51.37 71.60 51.11 63.14 53.11 68.67 57.20 62.30 51.34 41.06 38.54 47.74 51.92 54.11 34.36 51.37 28.22 51.11 46.30 53.11 61.45 57.20 43.73 51.34
Zhang_DKU_task2_4 ZhangDKU2023 76 47.856 63.43 64.16 49.63 64.30 51.42 64.94 51.84 66.34 49.68 71.17 50.77 54.60 53.80 61.06 50.38 36.59 34.52 49.63 47.90 51.42 39.12 51.84 25.70 49.68 35.34 50.77 54.97 53.80 32.77 50.38
Zhou_SHNU_task2_1 ZhouSHNU2023 32 58.542 73.06 70.12 51.37 73.36 64.16 73.08 51.05 81.18 49.79 71.76 51.99 73.41 61.51 69.61 55.94 51.93 41.66 51.37 68.52 64.16 30.86 51.05 53.28 49.79 66.69 51.99 65.16 61.51 68.07 55.94
Zhou_SHNU_task2_2 ZhouSHNU2023 69 49.781 67.92 70.12 51.37 73.36 64.16 73.08 51.05 81.18 49.79 68.17 50.28 47.68 49.34 73.90 50.36 38.04 41.66 51.37 68.52 64.16 30.86 51.05 53.28 49.79 26.21 50.28 39.04 49.34 32.79 50.36
Zhou_SHNU_task2_3 ZhouSHNU2023 10 63.645 64.98 53.72 55.74 56.66 52.11 66.60 59.53 68.88 63.53 71.76 51.99 73.41 61.51 69.61 55.94 70.57 70.82 55.74 69.02 52.11 70.86 59.53 87.42 63.53 66.69 51.99 65.16 61.51 68.07 55.94
Zhou_SHNU_task2_1 ZhouSHNU2023 32 58.542 73.06 70.12 51.37 73.36 64.16 73.08 51.05 81.18 49.79 71.76 51.99 73.41 61.51 69.61 55.94 51.93 41.66 51.37 68.52 64.16 30.86 51.05 53.28 49.79 66.69 51.99 65.16 61.51 68.07 55.94
Zhang_BIT_task2_1 ZhangBIT2023 28 59.489 74.61 84.62 51.89 66.54 57.21 69.54 57.32 88.84 60.47 71.78 50.09 69.44 61.32 76.89 61.06 51.54 37.58 51.89 58.06 57.21 59.58 57.32 41.76 60.47 54.61 50.09 55.60 61.32 66.90 61.06
Zhang_BIT_task2_2 ZhangBIT2023 56 54.210 74.84 87.10 49.05 54.98 52.16 79.48 51.63 89.24 52.79 82.09 51.38 67.16 58.67 76.87 58.08 43.14 27.44 49.05 51.18 52.16 35.18 51.63 36.58 52.79 57.88 51.38 57.75 58.67 62.86 58.08
Zhang_BIT_task2_3 ZhangBIT2023 67 49.944 47.69 43.80 48.63 47.44 51.68 49.32 48.21 47.16 49.95 47.31 50.85 57.55 52.42 43.70 49.08 52.28 47.34 48.63 53.40 51.68 50.06 48.21 46.96 49.95 57.49 50.85 59.89 52.42 53.52 49.08
Zhang_BIT_task2_4 ZhangBIT2023 43 56.271 67.08 76.24 51.05 86.22 55.47 59.56 54.58 76.06 55.47 56.84 48.76 63.11 61.47 61.49 56.25 49.88 35.06 51.05 56.64 55.47 68.12 54.58 40.24 55.47 48.74 48.76 53.83 61.47 64.41 56.25
Liu_CQUPT_task2_1 LiuCQUPT2023 44 56.003 67.46 52.42 48.79 70.90 55.53 77.52 57.84 82.18 57.74 58.19 51.54 74.91 62.70 66.77 60.40 47.88 44.84 48.79 57.52 55.53 43.44 57.84 29.70 57.74 53.11 51.54 64.72 62.70 64.36 60.40
Liu_CQUPT_task2_2 LiuCQUPT2023 64 50.419 63.68 46.00 48.74 41.28 49.58 81.08 50.26 86.44 52.16 74.24 54.00 70.26 56.16 80.89 53.84 40.72 49.68 48.74 58.28 49.58 25.86 50.26 24.22 52.16 54.54 54.00 46.25 56.16 67.95 53.84
Liu_CQUPT_task2_3 LiuCQUPT2023 48 55.594 69.58 48.36 48.63 60.44 53.37 79.50 56.58 87.30 56.74 73.09 54.31 77.57 59.42 78.27 59.31 46.53 47.38 48.63 59.82 53.37 37.54 56.58 28.70 56.74 53.84 54.31 55.51 59.42 68.80 59.31
Liu_CQUPT_task2_4 LiuCQUPT2023 45 55.667 69.19 48.40 48.58 59.10 52.63 79.70 56.95 87.56 57.11 72.13 54.38 77.23 59.29 78.05 60.15 46.81 47.38 48.58 59.54 52.63 38.52 56.95 28.86 57.11 53.61 54.38 55.90 59.29 69.08 60.15
Atmaja_AIST_task2_1 AtmajaAIST2023 53 54.898 57.77 49.24 54.11 74.22 53.11 48.02 52.32 78.32 63.32 52.93 50.26 51.25 48.29 64.94 53.48 53.92 63.18 54.11 37.86 53.11 64.40 52.32 65.62 63.32 54.27 50.26 45.71 48.29 60.55 53.48
Atmaja_AIST_task2_2 AtmajaAIST2023 51 55.049 57.81 49.24 54.00 74.56 54.05 47.96 51.05 78.00 63.74 53.10 50.26 51.07 48.29 65.43 53.43 54.36 63.90 54.00 39.04 54.05 63.30 51.05 68.26 63.74 53.61 50.26 45.37 48.29 61.11 53.43
Atmaja_AIST_task2_3 AtmajaAIST2023 52 54.928 57.63 49.66 54.00 73.86 53.58 47.18 51.95 78.08 62.74 52.89 50.43 51.22 48.29 65.16 53.81 54.11 63.68 54.00 38.36 53.58 64.06 51.95 66.28 62.74 54.04 50.43 45.27 48.29 61.32 53.81
Atmaja_AIST_task2_4 AtmajaAIST2023 50 55.092 57.65 49.24 54.00 74.08 53.00 47.30 51.84 79.38 64.11 52.91 50.31 51.16 48.29 64.81 54.28 54.48 63.72 54.00 38.10 53.00 63.88 51.84 71.06 64.11 53.88 50.31 45.37 48.29 61.69 54.28
Wilkinghoff_FKIE_task2_1 WilkinghoffFKIE2023 5 64.911 81.20 80.70 50.21 87.70 76.58 82.04 62.21 92.02 74.00 76.43 52.87 74.47 62.11 77.88 50.24 58.41 40.46 50.21 86.58 76.58 51.70 62.21 76.02 74.00 58.17 52.87 61.06 62.11 57.13 50.24
Wilkinghoff_FKIE_task2_2 WilkinghoffFKIE2023 18 61.949 77.82 83.66 50.95 83.58 70.16 83.68 54.89 96.30 68.26 65.86 49.66 69.68 55.97 70.60 50.86 56.17 35.90 50.95 83.50 70.16 45.34 54.89 67.96 68.26 57.28 49.66 67.40 55.97 63.60 50.86
Wilkinghoff_FKIE_task2_3 WilkinghoffFKIE2023 9 63.782 80.73 83.70 50.84 85.86 74.74 83.34 58.47 95.60 71.42 72.40 49.94 73.47 58.07 75.59 51.47 57.51 38.04 50.84 85.86 74.74 48.12 58.47 71.24 71.42 57.26 49.94 64.86 58.07 62.18 51.47
Jiang_PSH_task2_1 JiangPSH2023 71 48.919 48.23 33.82 52.84 67.28 56.05 42.56 51.95 63.70 51.11 50.75 49.46 49.16 50.47 46.61 49.46 47.19 69.46 52.84 35.88 56.05 70.96 51.95 30.50 51.11 47.19 49.46 57.41 50.47 48.62 49.46
Jiang_PSH_task2_2 JiangPSH2023 47 55.614 63.47 73.02 50.68 70.06 56.11 75.64 57.05 72.68 66.74 47.66 48.24 61.70 56.18 55.10 49.72 50.50 47.64 50.68 49.88 56.11 35.80 57.05 68.52 66.74 46.46 48.24 66.33 56.18 54.22 49.72
Jiang_PSH_task2_3 JiangPSH2023 66 49.990 82.59 80.68 51.37 72.00 51.47 85.96 48.74 89.98 48.47 79.84 51.60 82.46 63.31 90.33 71.97 33.94 29.86 51.37 34.10 51.47 22.66 48.74 23.46 48.47 39.16 51.60 60.14 63.31 69.08 71.97
Wu_qdreamer_task2_1 Wuqdreamer2023 62 51.526 62.60 74.03 48.21 68.28 49.58 59.06 55.84 98.18 63.68 52.55 48.02 48.30 48.76 59.47 55.59 43.24 31.32 48.21 30.68 49.58 64.60 55.84 43.82 63.68 50.18 48.02 51.27 48.76 50.91 55.59
Wu_qdreamer_task2_2 Wuqdreamer2023 37 57.896 75.97 77.36 48.95 94.26 62.47 85.56 57.47 96.96 63.16 56.94 51.44 69.62 57.79 68.11 57.48 47.70 27.24 48.95 59.32 62.47 60.34 57.47 42.84 63.16 48.81 51.44 59.26 57.79 62.82 57.48
Wu_qdreamer_task2_3 Wuqdreamer2023 29 59.263 57.64 34.20 52.53 89.08 60.26 84.88 57.89 44.78 65.26 60.52 50.81 60.76 54.21 71.99 58.87 63.89 69.52 52.53 71.00 60.26 58.78 57.89 77.50 65.26 51.21 50.81 59.75 54.21 67.07 58.87
Wu_qdreamer_task2_4 Wuqdreamer2023 36 57.988 54.84 33.16 52.16 86.20 58.32 39.46 55.26 91.32 65.63 59.25 50.83 61.04 51.20 61.18 53.20 65.53 68.20 52.16 71.64 58.32 81.16 55.26 75.44 65.63 49.68 50.83 57.07 51.20 66.76 53.20
Xiao_NJUPT_task2_1 XiaoNJUPT2023 38 57.612 69.49 64.68 50.89 80.68 52.21 79.36 57.68 82.24 63.05 61.87 48.72 66.40 58.16 59.20 50.77 52.10 66.60 50.89 47.24 52.21 59.90 57.68 42.34 63.05 47.85 48.72 51.95 58.16 56.43 50.77
Xiao_NJUPT_task2_2 XiaoNJUPT2023 70 49.022 76.00 81.52 49.79 77.36 50.26 88.38 53.79 91.48 54.58 76.51 51.15 63.19 55.92 63.41 50.61 34.62 29.68 49.79 27.14 50.26 25.82 53.79 24.90 54.58 59.86 51.15 50.54 55.92 61.46 50.61
Xiao_NJUPT_task2_2 XiaoNJUPT2023 70 49.022 76.00 81.52 49.79 77.36 50.26 88.38 53.79 91.48 54.58 76.51 51.15 63.19 55.92 63.41 50.61 34.62 29.68 49.79 27.14 50.26 25.82 53.79 24.90 54.58 59.86 51.15 50.54 55.92 61.46 50.61
Jie_IESEFPT_task2_1 JieIESEFPT2023 3 65.627 85.29 82.54 51.26 96.36 74.84 88.56 62.63 100.00 84.79 77.26 53.06 73.88 60.82 84.68 52.91 56.86 41.34 51.26 79.76 74.84 47.26 62.63 89.78 84.79 55.84 53.06 58.92 60.82 52.10 52.91
Jie_IESEFPT_task2_2 JieIESEFPT2023 1 66.969 83.13 80.26 51.58 90.42 77.74 84.80 61.53 96.90 85.32 76.55 53.35 73.67 62.45 83.76 55.97 60.08 45.44 51.58 87.68 77.74 46.82 61.53 95.48 85.32 57.49 53.35 60.82 62.45 57.34 55.97
Jie_IESEFPT_task2_3 JieIESEFPT2023 25 60.232 79.23 89.58 49.68 62.58 51.89 83.10 53.53 88.66 68.79 80.49 57.25 73.80 62.58 83.90 63.43 50.55 27.92 49.68 63.42 51.89 39.60 53.53 64.40 68.79 68.04 57.25 58.72 62.58 69.52 63.43
Jie_IESEFPT_task2_4 JieIESEFPT2023 72 48.706 68.07 85.30 48.16 80.46 56.16 90.22 54.58 92.74 52.11 60.66 49.65 57.04 51.31 43.85 48.92 36.43 23.66 48.16 62.92 56.16 47.84 54.58 19.72 52.11 50.48 49.65 47.86 51.31 46.11 48.92
Gou_UESTC_task2_1 GouUESTC2023 75 47.952 62.65 76.02 50.11 59.48 54.84 71.48 52.32 77.72 49.37 54.30 52.58 54.03 53.63 55.59 52.76 36.45 27.65 50.11 54.96 54.84 31.52 52.32 23.79 49.37 52.20 52.58 55.29 53.63 37.52 52.76
Gou_UESTC_task2_2 GouUESTC2023 81 46.157 58.38 86.66 50.11 50.18 49.16 85.00 50.32 83.62 52.89 48.27 53.35 42.55 49.71 48.77 49.46 35.55 25.50 50.11 66.20 49.16 29.32 50.32 25.58 52.89 42.26 53.35 44.54 49.71 42.99 49.46
Gou_UESTC_task2_3 GouUESTC2023 73 48.690 61.46 87.24 48.47 50.60 50.11 80.44 54.47 78.78 49.42 61.11 52.61 49.47 49.51 47.70 49.14 39.18 27.94 48.47 64.52 50.11 30.24 54.47 27.98 49.42 51.21 52.61 47.08 49.51 56.16 49.14
Gou_UESTC_task2_4 GouUESTC2023 82 45.962 63.07 73.18 49.05 64.54 53.16 72.46 50.00 78.64 49.58 51.36 51.95 61.80 54.79 50.86 49.81 33.50 23.58 49.05 57.80 53.16 23.76 50.00 18.72 49.58 55.98 51.95 57.46 54.79 54.12 49.81
Tanaka_GU_task2_1 TanakaGU2023 61 52.545 72.49 83.82 51.00 74.94 54.42 82.18 51.84 92.16 59.95 66.69 52.90 63.29 54.59 57.20 48.49 40.87 27.56 51.00 45.62 54.42 32.06 51.84 46.72 59.95 50.11 52.90 60.96 54.59 41.43 48.49
Tanaka_GU_task2_2 TanakaGU2023 63 50.812 55.60 67.58 52.89 61.36 51.42 48.00 48.32 61.42 48.89 52.63 50.04 53.37 53.12 50.11 50.02 46.96 48.98 52.89 57.68 51.42 51.44 48.32 24.56 48.89 60.27 50.04 57.12 53.12 58.59 50.02
Tanaka_GU_task2_3 TanakaGU2023 49 55.253 69.54 86.48 48.21 78.94 52.74 69.38 59.11 87.08 62.84 53.79 51.25 62.14 55.39 63.10 58.62 45.98 24.26 48.21 49.66 52.74 69.38 59.11 45.10 62.84 50.57 51.25 58.04 55.39 57.79 58.62
Tanaka_GU_task2_4 TanakaGU2023 79 46.623 38.50 30.76 50.37 54.14 53.11 35.24 52.05 26.00 50.79 46.19 51.89 56.48 52.17 40.59 50.84 52.66 77.26 50.37 31.72 53.11 65.04 52.05 77.90 50.79 56.03 51.89 59.02 52.17 39.30 50.84
Fujimura_NU_task2_1 FujimuraNU2023 54 54.701 83.45 91.02 49.32 88.58 61.47 85.20 54.47 84.40 61.37 82.36 53.75 72.09 61.08 83.30 59.84 39.52 20.60 49.32 59.74 61.47 43.92 54.47 44.62 61.37 46.00 53.75 54.09 61.08 37.80 59.84
Fujimura_NU_task2_2 FujimuraNU2023 58 53.760 83.30 88.36 49.79 88.86 57.58 83.68 55.32 83.74 59.63 83.03 53.33 73.14 58.84 84.33 58.99 38.55 22.14 49.79 53.14 57.58 40.80 55.32 45.08 59.63 43.63 53.33 50.78 58.84 35.33 58.99
Fujimura_NU_task2_3 FujimuraNU2023 55 54.282 73.03 84.14 49.37 75.98 58.95 81.28 52.68 81.54 58.16 66.26 51.26 60.35 59.10 68.60 60.60 42.50 23.84 49.37 53.68 58.95 36.12 52.68 47.28 58.16 51.48 51.26 54.09 59.10 57.58 60.60
Fujimura_NU_task2_4 FujimuraNU2023 59 53.508 81.56 88.10 49.21 88.62 60.16 83.52 53.00 83.54 59.26 81.44 52.60 67.60 60.22 82.11 59.63 38.56 20.26 49.21 56.34 60.16 37.96 53.00 46.02 59.26 45.21 52.60 54.04 60.22 38.83 59.63
Bai_JLESS_task2_1 BaiJLESS2023 12 63.545 71.91 79.26 51.11 58.08 51.79 81.68 54.63 62.24 62.84 80.70 55.75 72.54 62.19 76.79 63.81 63.43 49.72 51.11 63.22 51.79 51.30 54.63 93.24 62.84 68.70 55.75 58.63 62.19 79.43 63.81
Bai_JLESS_task2_2 BaiJLESS2023 13 63.516 70.88 74.98 51.11 57.72 52.53 76.86 52.89 57.36 62.37 80.19 54.58 73.68 62.57 86.15 67.62 64.08 47.08 51.11 64.64 52.53 60.00 52.89 94.78 62.37 63.08 54.58 61.40 62.57 75.95 67.62
Bai_JLESS_task2_3 BaiJLESS2023 6 64.104 69.49 57.72 50.89 54.40 51.16 77.46 59.58 73.12 69.47 78.59 55.65 73.26 63.03 82.83 63.37 65.51 46.40 50.89 66.52 51.16 63.94 59.58 91.94 69.47 70.82 55.65 61.84 63.03 74.24 63.37
Bai_JLESS_task2_4 BaiJLESS2023 22 61.349 76.62 85.68 52.05 56.12 51.42 82.30 54.05 87.90 66.11 79.33 56.93 72.68 61.06 83.45 64.52 54.18 34.64 52.05 59.04 51.42 48.02 54.05 67.28 66.11 65.94 56.93 57.12 61.06 66.49 64.52
Guan_HEU_task2_1 GuanHEU2023 46 55.620 65.18 75.64 50.84 70.62 55.05 79.30 57.05 96.40 72.58 60.52 49.71 56.30 50.60 43.95 48.76 49.78 44.08 50.84 51.96 55.05 49.76 57.05 59.28 72.58 51.10 49.71 48.20 50.60 46.70 48.76
Guan_HEU_task2_2 GuanHEU2023 16 62.408 76.47 76.20 50.74 70.32 54.16 89.14 57.47 97.60 75.84 65.34 50.51 64.29 54.98 84.25 68.50 56.63 43.68 50.74 59.28 54.16 48.24 57.47 71.82 75.84 51.87 50.51 59.41 54.98 76.42 68.50
Guan_HEU_task2_3 GuanHEU2023 40 57.267 58.19 39.92 53.37 73.88 55.84 55.58 57.84 56.80 54.89 61.75 50.32 64.54 50.76 69.37 50.89 60.85 70.84 53.37 64.50 55.84 71.06 57.84 53.68 54.89 50.23 50.32 57.12 50.76 65.37 50.89
Guan_HEU_task2_4 GuanHEU2023 14 63.503 76.72 73.36 52.05 76.08 54.21 87.06 60.63 94.96 72.47 66.20 50.76 66.45 54.96 81.30 61.47 59.66 55.10 52.05 63.02 54.21 53.68 60.63 68.32 72.47 50.39 50.76 58.77 54.96 75.82 61.47
Hauser_JKU_task2_1 HauserJKU2023 86 41.407 30.39 30.04 48.47 26.94 48.74 30.60 50.32 16.18 47.89 51.71 51.26 42.52 49.08 44.26 48.23 52.13 63.08 48.47 56.98 48.74 49.60 50.32 65.50 47.89 54.02 51.26 41.33 49.08 43.96 48.23
LEE_KNU_task2_1 LEEKNU2023 85 43.738 32.22 27.70 50.05 36.58 52.05 24.68 51.32 21.62 50.42 43.30 47.37 42.27 48.48 49.33 51.13 56.87 70.06 50.05 52.72 52.05 75.60 51.32 76.94 50.42 42.92 47.37 52.24 48.48 47.20 51.13
LEE_KNU_task2_2 LEEKNU2023 84 44.232 33.45 28.58 50.21 38.72 51.58 25.60 51.68 22.74 49.53 43.12 47.37 43.17 48.50 52.44 52.08 55.68 66.76 50.21 47.58 51.58 80.26 51.68 77.84 49.53 43.95 47.37 50.19 48.50 46.00 52.08
LEE_KNU_task2_3 LEEKNU2023 88 40.809 29.94 27.10 48.79 35.72 51.79 22.16 49.74 17.10 48.26 49.34 49.92 48.76 48.63 40.84 49.26 50.25 72.56 48.79 57.58 51.79 73.84 49.74 76.82 48.26 50.39 49.92 27.49 48.63 39.43 49.26
LEE_KNU_task2_4 LEEKNU2023 87 41.254 30.42 30.94 49.37 37.36 49.89 22.34 50.89 15.44 47.95 49.97 49.63 48.57 48.59 47.85 51.27 50.77 69.50 49.37 53.90 49.89 75.74 50.89 81.70 47.95 49.13 49.63 28.41 48.59 41.74 51.27
QianXuHu_BITNUDT_task2_1 QianXuHuBITNUDT2023 39 57.470 59.48 62.12 51.37 90.22 58.32 59.48 62.16 57.70 62.79 54.57 52.47 46.71 47.37 60.11 53.08 58.30 59.14 51.37 67.00 58.32 57.34 62.16 88.42 62.79 55.07 52.47 39.42 47.37 62.63 53.08
QianXuHu_BITNUDT_task2_2 QianXuHuBITNUDT2023 42 56.317 66.37 62.12 51.37 90.22 58.32 84.44 54.68 99.20 59.79 54.57 52.47 46.71 47.37 60.11 53.08 51.18 59.14 51.37 67.00 58.32 46.90 54.68 41.44 59.79 55.07 52.47 39.42 47.37 62.63 53.08
QianXuHu_BITNUDT_task2_3 QianXuHuBITNUDT2023 31 59.062 64.14 60.10 53.00 34.86 51.53 87.28 59.42 85.38 62.58 74.50 53.03 72.88 59.02 74.07 55.41 57.62 55.60 53.00 70.66 51.53 51.46 59.42 63.34 62.58 55.14 53.03 47.86 59.02 66.24 55.41
QianXuHu_BITNUDT_task2_4 QianXuHuBITNUDT2023 60 53.390 49.32 60.10 53.00 34.86 51.53 29.30 52.16 45.82 51.16 74.50 53.03 72.88 59.02 74.07 55.41 58.06 55.60 53.00 70.66 51.53 73.10 52.16 48.50 51.16 55.14 53.03 47.86 59.02 66.24 55.41



System characteristics

Summary of the submitted system characteristics.

Rank Submission
Code 		Technical
Report 		Classifier System
Complexity 		Acoustic
Feature 		Data
Augmentation 		Decision Making System
Embeddings 		Subsystem
Conut 		External
Data Usage 		Front End
System
24 DCASE2023_baseline_task2_MAHALA DCASE2023baseline2023 AE 267928 log-mel energies
30 DCASE2023_baseline_task2_MSE DCASE2023baseline2023 AE 267928 log-mel energies
21 Du_NERCSLIP_task2_1 DuNERCSLIP2023 CNN, AE, ensemble 107708217 mel spectrogram, raw waveform mixup weighted average wav2vec 3
19 Du_NERCSLIP_task2_2 DuNERCSLIP2023 CNN, AE, ensemble 107708002 mel spectrogram, raw waveform mixup weighted average wav2vec 2
20 Du_NERCSLIP_task2_3 DuNERCSLIP2023 CNN, AE, ensemble 5469799 mel spectrogram mixup weighted average 2
23 Du_NERCSLIP_task2_4 DuNERCSLIP2023 CNN, AE, ensemble 107707961 mel spectrogram, raw waveform mixup weighted average wav2vec 2
78 He_XJU_task2_1 HeXJU2023 CNN 269992 spectrogram pitch shifting
83 He_XJU_task2_2 HeXJU2023 CNN 269992 spectrogram pitch shifting
80 He_XJU_task2_3 HeXJU2023 CNN 269992 spectrogram pitch shifting
74 He_XJU_task2_4 HeXJU2023 CNN 269992 spectrogram pitch shifting
11 Lv_HUAKONG_task2_1 LvHUAKONG2023 Transformer 300000000 raw waveform median wav2vec2, hubert, unispeech, wavlm 4 wav2vec2
15 Lv_HUAKONG_task2_2 LvHUAKONG2023 Transformer 300000000 raw waveform median wav2vec2 4 wav2vec2
8 Lv_HUAKONG_task2_3 LvHUAKONG2023 Transformer 300000000 raw waveform median wav2vec2, unispeech, wavlm 6 wav2vec2
2 Lv_HUAKONG_task2_4 LvHUAKONG2023 Transformer 300000000 raw waveform median wav2vec2, unispeech, wavlm 3 wav2vec2, unispeech, wavlm
4 Jiang_THUEE_task2_1 JiangTHUEE2023 NFCDEE 6574848 log-mel energies median
35 Jiang_THUEE_task2_2 JiangTHUEE2023 classifier, nfcdee 1.206B log-mel energies median wav2vec, hubert, unispeech, wavlm 6 wav2vec, hubert, unispeech, wavlm
7 Jiang_THUEE_task2_3 JiangTHUEE2023 classifier, nfcdee 1.206B log-mel energies median wav2vec, hubert, unispeech, wavlm 6 wav2vec, hubert, unispeech, wavlm
17 Jiang_THUEE_task2_4 JiangTHUEE2023 classifier, nfcdee 1.206B log-mel energies median wav2vec, hubert, unispeech, wavlm 6 wav2vec, hubert, unispeech, wavlm
33 JiaJun_HFUU_task2_1 JiaJunHFUU2023 GMM,KNN,CNN,LOF,Transformer,ensemble 4971030 log-mel energies smote,mixup 3
33 JiaJun_HFUU_task2_2 JiaJunHFUU2023 GMM,KNN,CNN,LOF,Transformer,ensemble 4971030 log-mel energies smote,mixup 3
27 JiaJun_HFUU_task2_3 JiaJunHFUU2023 GMM,KNN,CNN,LOF,Transformer,ensemble 4971030 log-mel energies smote,mixup 3
41 JiaJun_HFUU_task2_4 JiaJunHFUU2023 GMM,KNN,CNN,LOF,Transformer,ensemble 4971030 log-mel energies smote,mixup 3
76 Zhang_DKU_task2_1 ZhangDKU2023 conformer, GMM 10.53M log-mel spectrogram mixup,pitch shifting,time stretching,gaussian noise,fading,time shifting,time masking,frequency masking
57 Zhang_DKU_task2_2 ZhangDKU2023 CNN, conformer, GMM 12.91M log-mel spectrogram, raw waveform mixup,pitch shifting,time stretching,gaussian noise,fading,time shifting,time masking,frequency masking
65 Zhang_DKU_task2_3 ZhangDKU2023 CNN, VAE 1.3M log-mel spectrogram
76 Zhang_DKU_task2_4 ZhangDKU2023 CNN, conformer, VAE, GMM 24.74M log-mel spectrogram, raw waveform mixup,pitch shifting,time stretching,gaussian noise,fading,time shifting,time masking,frequency masking average 3
32 Zhou_SHNU_task2_1 ZhouSHNU2023 ResNet, KNN 11171280 log-mel energies gaussian noise, time stretching, pitch shifting, shifting 2
69 Zhou_SHNU_task2_2 ZhouSHNU2023 ResNet, KNN 11171280 log-mel energies gaussian noise, time stretching, pitch shifting, shifting
10 Zhou_SHNU_task2_3 ZhouSHNU2023 AE 269992 log-mel energies gaussian noise, time stretching, pitch shifting, shifting 2
32 Zhou_SHNU_task2_1 ZhouSHNU2023 ResNet, KNN 11171280 log-mel energies gaussian noise, time stretching, pitch shifting, shifting 2
28 Zhang_BIT_task2_1 ZhangBIT2023 VAE 35704705 STFT spectrum
56 Zhang_BIT_task2_2 ZhangBIT2023 VAE, Contrastive Learning 35704705 STFT spectrum
67 Zhang_BIT_task2_3 ZhangBIT2023 VAE, GMM 229948 log-mel energies
43 Zhang_BIT_task2_4 ZhangBIT2023 CNN, Denoising Diffusion Probability Model 35704705 log-mel energies
44 Liu_CQUPT_task2_1 LiuCQUPT2023 CNN 3706766 log-mel energies average 2 pre-trained model
64 Liu_CQUPT_task2_2 LiuCQUPT2023 ViT 486172 log-mel energies average 2
48 Liu_CQUPT_task2_3 LiuCQUPT2023 CNN, ViT 4192938 log-mel energies average 4 pre-trained model
45 Liu_CQUPT_task2_4 LiuCQUPT2023 CNN, ViT 4192938 log-mel energies average 4 pre-trained model
53 Atmaja_AIST_task2_1 AtmajaAIST2023 AE 269992 log-mel energies
51 Atmaja_AIST_task2_2 AtmajaAIST2023 AE 269992 log-mel energies
52 Atmaja_AIST_task2_3 AtmajaAIST2023 AE 269992 log-mel energies
50 Atmaja_AIST_task2_4 AtmajaAIST2023 AE 269992 log-mel energies
5 Wilkinghoff_FKIE_task2_1 WilkinghoffFKIE2023 CNN, ensemble 34417490 magnitude spectrogram, magnitude spectrum mixup sum 10
18 Wilkinghoff_FKIE_task2_2 WilkinghoffFKIE2023 CNN, ensemble 42036050 magnitude spectrogram, magnitude spectrum mixup maximum 10
9 Wilkinghoff_FKIE_task2_3 WilkinghoffFKIE2023 CNN, ensemble 76453540 magnitude spectrogram, magnitude spectrum mixup maximum, average 20
71 Jiang_PSH_task2_1 JiangPSH2023 CNN 1657392 kaldi.fbank
47 Jiang_PSH_task2_2 JiangPSH2023 CNN 779992 log-mel energies pitch shifting IDMT-ISA-ELECTRIC-ENGINE
66 Jiang_PSH_task2_3 JiangPSH2023 CNN 779992 log-mel energies pitch shifting IDMT-ISA-ELECTRIC-ENGINE
62 Wu_qdreamer_task2_1 Wuqdreamer2023 AE, GAN, CNN 269992 log-mel spectrogram simulation of anomalous samples PCA
37 Wu_qdreamer_task2_2 Wuqdreamer2023 AE, GAN, CNN 269992 log-mel spectrogram simulation of anomalous samples PCA
29 Wu_qdreamer_task2_3 Wuqdreamer2023 AE, GAN, CNN 269992 log-mel spectrogram simulation of anomalous samples PCA
36 Wu_qdreamer_task2_4 Wuqdreamer2023 AE, GAN, CNN 269992 log-mel spectrogram simulation of anomalous samples PCA
38 Xiao_NJUPT_task2_1 XiaoNJUPT2023 AE 221809 spectral coherence, wavelet, log-mel
70 Xiao_NJUPT_task2_2 XiaoNJUPT2023 GMM 0 spectral coherence, wavelet, log-mel
70 Xiao_NJUPT_task2_2 XiaoNJUPT2023 CNN 713910 spectral coherence, wavelet, log-mel
3 Jie_IESEFPT_task2_1 JieIESEFPT2023 CNN,KNN,smote 3124602 spectrum mixup
1 Jie_IESEFPT_task2_2 JieIESEFPT2023 CNN,cosine distance,smote 3135603 spectrum mixup
25 Jie_IESEFPT_task2_3 JieIESEFPT2023 AE,ensemble 3105433 log-mel energies mixup
72 Jie_IESEFPT_task2_4 JieIESEFPT2023 cnn,ensemble 3010000 log-mel energies mixup
75 Gou_UESTC_task2_1 GouUESTC2023 AE, CAE, LOF, CNN 1198336 log-mel energies mixup, pitch shifting, time masking, frequency masking, gaussian noise
81 Gou_UESTC_task2_2 GouUESTC2023 CNN 1058816 log-mel energies Spectral noise addition, Spectral masking, Spectral warping
73 Gou_UESTC_task2_3 GouUESTC2023 CNN 1058816 log-mel energies Spectral noise addition, Spectral masking, Spectral warping
82 Gou_UESTC_task2_4 GouUESTC2023 AE, CAE, LOF, CNN 1198336 log-mel energies mixup, pitch shifting, time masking, frequency masking, gaussian noise
61 Tanaka_GU_task2_1 TanakaGU2023 CNN, Mahalanobis distance 11234503 log-mel spectrogram frequency masking, time masking, gaussian noise
63 Tanaka_GU_task2_2 TanakaGU2023 CNN,AE 2,062,744 log-mel energies streching 7
49 Tanaka_GU_task2_3 TanakaGU2023 CNN 11365312 log-mel spectrogram gaussian noise
79 Tanaka_GU_task2_4 TanakaGU2023 ensemble 11234503 log-mel spectrogram
54 Fujimura_NU_task2_1 FujimuraNU2023 GMM,KNN,normalizing flow,CNN 189652039 mel spectrogram mixup average PyTorch Image Models 84 pre-trained model
58 Fujimura_NU_task2_2 FujimuraNU2023 GMM,KNN,normalizing flow,CNN 118784132 mel spectrogram mixup average PyTorch Image Models 42 pre-trained model
55 Fujimura_NU_task2_3 FujimuraNU2023 GMM,KNN,normalizing flow,CNN 100559620 mel spectrogram mixup average PyTorch Image Models 81 pre-trained model
59 Fujimura_NU_task2_4 FujimuraNU2023 GMM,KNN,normalizing flow,CNN 83 mel spectrogram mixup average PyTorch Image Models 159953414 pre-trained model
12 Bai_JLESS_task2_1 BaiJLESS2023 VAE, GAN 2.4M log-mel energies mixup
13 Bai_JLESS_task2_2 BaiJLESS2023 VAE, GAN 2.4M log-mel energies mixup
6 Bai_JLESS_task2_3 BaiJLESS2023 VAE 2.4M log-mel energies mixup
22 Bai_JLESS_task2_4 BaiJLESS2023 VAE 2.4M log-mel energies mixup
46 Guan_HEU_task2_1 GuanHEU2023 GMM 33024 log-mel energies smote
16 Guan_HEU_task2_2 GuanHEU2023 GMM 33024 log-mel energies smote AudioLDM
40 Guan_HEU_task2_3 GuanHEU2023 CNN 84604468 log-mel energies pretrained CNN14 in PANNs
14 Guan_HEU_task2_4 GuanHEU2023 GMM, CNN 84670516 log-mel energies smote weighted average 3 AudioLDM, pretrained CNN14 in PANNs
86 Hauser_JKU_task2_1 HauserJKU2023 AE, U-net 17265985 log-mel spectrogram
85 LEE_KNU_task2_1 LEEKNU2023 contrastive learning, maximum likelihook covariance estimator 11496000 log-mel spectrogram pitch shifting, gaussian noise, time masking
84 LEE_KNU_task2_2 LEEKNU2023 contrastive learning, elliptic envelope 11496000 log-mel spectrogram pitch shifting, gaussian noise, time masking
88 LEE_KNU_task2_3 LEEKNU2023 contrastive learning, maximum likelihook covariance estimator 11496000 log-mel spectrogram pitch shifting, gaussian noise, time masking
87 LEE_KNU_task2_4 LEEKNU2023 contrastive learning, elliptic envelope 11496000 log-mel spectrogram pitch shifting, gaussian noise, time masking
39 QianXuHu_BITNUDT_task2_1 QianXuHuBITNUDT2023 GAN 269992 spectrogram
42 QianXuHu_BITNUDT_task2_2 QianXuHuBITNUDT2023 GAN 269992 spectrogram
31 QianXuHu_BITNUDT_task2_3 QianXuHuBITNUDT2023 AE log-mel energies
60 QianXuHu_BITNUDT_task2_4 QianXuHuBITNUDT2023 AE log-mel energies



System output for submitted systems

DCASE2023 Task 2 system outputs (2.0 MB)
(.zip)


Technical reports

ON THE USE OF CONCORDANCE CORRELATION COEFFICIENT FOR EVALUATING FIRST SHOT ANOMALOUS SOUND DETECTION

Bagus Tris Atmaja, Akira Sasou
Signal Processing Research Team, National Institute of Advanced Industrial Science and Technology (AIST), Tsukuba, Japan

Abstract

The choice of the loss function is a critical aspect of machine/deep learning. In this study, we investigate the use of the concordance correlation coefficient (CCC) as a loss function for first-shot anomaly sound detection. We compare the performance of CCC with the commonly used loss function, mean squared error (MSE). Furthermore, we benchmark CCC, MSE, and selective Malahanobis distance equally. The results show that CCC outperforms MSE and Selective Mahalanobis in terms of the harmonic mean of pAUC scores. We repeated the experiments of our method with CCC five times, and we obtained similar results across four runs showing the stability of our method.

System characteristics
Classifier AE
System complexity 269992
Acoustic features log-mel energies
PDF

Unsupervised Abnormal Sound Detection Based on Machine Condition Mixup

Yafei Jia, Jisheng Bai, Siwei Huang, Jianfeng Chen
Joint Laboratory of Environmental Sound Sensing, School of Marine Science and Technology, Northwestern Polytechnical University., Xi'an, China and 1 Joint Laboratory of Environmental Sound Sensing, School of Marine Science and Technology, Northwestern Polytechnical University, 2 LianFeng Acoustic Technologies Co., Ltd., Xi'an, China

Abstract

Anomaly detection has a wide range of applications such as finding fraud cases in industry or indicating network intrusion in network security. Anomalous sound detection (ASD) for machine condition monitoring can detect anomalies in advance and prevent causing damage. However, the operational conditions of machines often change, leading to the different acoustic characteristics between training and test data. Domain generalization techniques are required to adapt the model to different conditions. In this paper, we present an unsupervised method for ASD, which uses MSE, KLD, and BCE as joint loss and Condition-Mixup data augmentation strategies for the GAN-VAE model. The proposed Condition-Mixup strategy mixes data from the target domain of the unified condition in the time domain to balance the difference in data volume between the source domain and the target domain. In addition, we adopted a GAN-VAE model to learn common potential information between the source and target domains. Finally, we use acoustic representation to train anomaly detectors to detect abnormal sounds. The experimental results on the DCASE2023 taks2 development dataset show that our method outperforms the baseline system.

System characteristics
Classifier GAN, VAE
System complexity 2.4M
Acoustic features log-mel energies
Data augmentation mixup
PDF

Description and Discussion on DCASE 2023 Challenge Task 2: First-Shot Unsupervised Anomalous Sound Detection for Machine Condition Monitoring

Kota Dohi, Keisuke Imoto, Noboru Harada, Daisuke Niizumi, Yuma Koizumi, Tomoya Nishida, Harsh Purohit, Ryo Tanabe, Takashi Endo, Yohei Kawaguchi
Research and Development Group, Hitachi, Ltd., Tokyo, Japan and Doshisha University, Kyoto, Japan and NTT Communication Science Labs, Kanagawa, Japan

Abstract

We present the task description of the Detection and Classification of Acoustic Scenes and Events (DCASE) 2023 Challenge Task 2: "First-shot unsupervised anomalous sound detection (ASD) for machine condition monitoring". The main goal is to enable rapid deployment of ASD systems for new kinds of machines using only a few normal samples, without the need for hyperparameter tuning. In the past ASD tasks, developed methods tuned hyperparameters for each machine type, as the development and evaluation datasets had the same machine types. However, collecting normal and anomalous data as the development dataset can be infeasible in practice. In 2023 Task 2, we focus on solving first-shot problem, which is the challenge of training a model on a few machines of a completely novel machine type. Specifically, (i) each machine type has only one section, and (ii) machine types in the development and evaluation datasets are completely different. We will add challenge results and analysis of the submissions after the challenge submission deadline.

System characteristics
Classifier AE
System complexity 267928
Acoustic features log-mel energies
PDF

FIRST-SHOT UNSUPERVISED ANOMALOUS SOUND DETECTION USING ATTRIBUTE CLASSIFICATION AND CONDITIONAL AUTOENCODER

Lei Wang, Fan Chu, Yuxuan Zhou, Shuxian Wang, Zulong Yan, Shifan Xu, Qing Wu, Mingqi Cai, Jia Pan, Qing Wang, Jun Du, Tian Gao, Xin Fang, Liang Zou
National Intelligent Voice Innovation Center, Hefei, China and University of Science and Technology of China, Hefei, China and China University of Mining and Technology, Xuzhou, China and IFLYTEK CO. LTD., Hefei, China and National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China

Abstract

This technical report outlines our solution to DCASE 2023 Challenge Task 2, First-Shot Unsupervised Anomalous Sound Detection for Machine Condition Monitoring. This year's task focuses on the first-shot problem: the development dataset and the evaluation dataset have completely different sets of machine types, and each machine type contains only one section. We propose an anomaly detection method based on attribute classification and conditional autoencoder. The attribute classification method includes model pre-training, embedding extraction and inlier modeling, and the conditional autoencoder uses attribute information as conditions. The proposed system achieves 78.35% in the harmonic mean of all machine types, sections, and domains for the area under the curve (AUC) and partial AUC (p = 0.1) on the development set.

System characteristics
Classifier AE, CNN, ensemble
System complexity 107707961, 107708002, 107708217, 5469799
Acoustic features mel spectrogram, raw waveform
Data augmentation mixup
Decision making weighted average
System embeddings wav2vec
Subsystem count 2, 3
PDF

Anomalous sound detection by end-to-end training of outlier exposure and normalizing flow with domain generalization techniques

Takuya Fujimura, Ibuki Kuroyanagi, Tomoki Hayashi, Tomoki Toda
Nagoya University, Nagoya, Japan and Nagoya University and Human Dataware Lab. Co., Ltd., Nagoya, Japan

Abstract

In this report, we propose an anomalous sound detection (ASD) method for DCASE 2023 Challenge Task 2. Our proposed method is an extension of the serial approach using an outlier exposure-based feature extractor and an inlier modeling-based anomalous detector. We newly employ the normalizing flow as the inlier model and jointly optimize it with the feature extractor in an end-to-end manner. Furthermore, in order to deal with the domain shift, we use some domain generalization techniques, such as the domain-invariant latent space modeling in the normalizing flow and mixup to generate the pseudo-target domain data. The anomaly scores can be calculated directly using the normalizing flow or additionally using other inlier models separately trained with the optimized feature embeddings. Our final system is made by the ensemble and achieves 69.78 % in the harmonic mean of the area under the curve (AUC) and partial AUC (p=0.1) over all machine types and domains on the development set.

System characteristics
Classifier CNN, GMM, KNN, normalizing flow
System complexity 100559620, 118784132, 189652039, 83
Acoustic features mel spectrogram
Data augmentation mixup
Decision making average
System embeddings PyTorch Image Models
Subsystem count 159953414, 42, 81, 84
External data usage pre-trained model
PDF

A DATA AUGMENTATION-BASED APPROACH FOR FIRST-SHOT UNSUPERVISED ANOMALOUS SOUND DETECTION

Jiacheng Gou, Chenkun Sun, Anqi Tu, Huiyong Li, Chuang Shi
School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China and University of Electronic Science and Technology of China, Chengdu, China

Abstract

The detection of abnormal conditions in machinery and equipment through sound diagnosis is of utmost importance in the field of industrial automation. However, acquiring abnormal sound and dealing with machine state transformation can present challenges. In order to address these challenges, a data augmentation combined with unsupervised feature extraction approach has been proposed for abnormal sound detection in machinery and equipment. The method involves the extraction of features from the sound samples using a unsupervised feature extractor, which is constructed using both normal and artificially constructed abnormal log-mel-spectrograms. These features are then fed into a autoencoder for unsupervised abnormal sound recognition. The proposed method has been evaluated using the DCASE 2023 Task 2 Development Dataset, and the results demonstrate that it can adaptively extract sound features of mechanical equipment, achieving an average area under the curve detection result of 56.52%.

System characteristics
Classifier AE, CAE, CNN, LOF
System complexity 1058816, 1198336
Acoustic features log-mel energies
Data augmentation Spectral noise addition, Spectral masking, Spectral warping, mixup, pitch shifting, time masking, frequency masking, gaussian noise
PDF

First-shot Anomalous Sound Detection with GMM Clustering and Finetuned Attribute Classification using Audio Pretrained Model

Jiantong Tian, Hejing Zhang, Qiaoxi Zhu, Feiyang Xiao, Haohe Liu, Xinhao Mei, Youde Liu, Wenwu Wang, Jian Guan
Group of Intelligent Signal Processing, College of Computer Science and Technology, Harbin Engineering University, Harbin, China and Centre for Audio, Acoustic and Vibration, University of Technology Sydney, Ultimo, Australia and Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, UK and School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China

Abstract

This technical report describes our submission for DCASE 2023 challenge task 2. To address the first-shot and domain shift problem in anomalous sound detection (ASD), we designed an ensemble system that consists of a classification method based on pretrained audio neural networks (PANNs) and a clustering method based on the Gaussian Mixture Model (GMM) with a text-to-audio pretrained model AudioLDM. Experiments on the development set show that our system achieved 77.6% in the harmonic mean of area under curve (AUC) in the source domain, 65.4% in AUC in the target domain, and 56.6% in pAUC across all machine types.

System characteristics
Classifier CNN, GMM
System complexity 33024, 84604468, 84670516
Acoustic features log-mel energies
Data augmentation smote
Decision making weighted average
Subsystem count 3
External data usage AudioLDM, AudioLDM, pretrained CNN14 in PANNs, pretrained CNN14 in PANNs
PDF

ANOMALY DETECTION USING SPECTROGRAM RECONSTRUCTION ERRORS WITH U-NET

David Hauser, Tobias Katsch, Sara Moosbauer
Johannes Kepler University, Linz, Austria

Abstract

In this report we describe our submission to the DCASE 2023 Task 2: First-Shot Unsupervised Anomalous Sound Detection Challenge, which has the goal of detecting malfunctioning machines by analyzing a machine's sound recording. We applied the U-Net architecture, trained to reconstruct partially masked spectrograms generated from the machine sound recordings. The task turned out to be challenging, beating the baseline on one out of seven machines during evaluation.

System characteristics
Classifier AE, U-net
System complexity 17265985
Acoustic features log-mel spectrogram
PDF

Unsupervised abnormal sound detection method based on causal separation

Yunxiang Zhang, Zheng Yaohao, Luo Qingqing, Liang HE
School of Information Science and Engineering, Xinjiang University, Urumqi, China and Xinjiang University, Urumqi, China

Abstract

Anomalous sound detection (ASD) is the task of identifying if a sound is normal or anomalous with respect to a given reference. In this report we present a solution for the DCASE2023 task 2 (First-Shot Unsupervised Anomalous Sound Detection for Machine Condition Monitoring), which aims to address the ASD problem under domain generalization and First-shot problem. We use the method consists of the classification method and stable learning. The proposed systems achieve in the harmonic mean of all machine types, sections, and domains for the area under the curve (AUC) and partial AUC (p = 0.1) on the development set.

System characteristics
Classifier CNN
System complexity 269992
Acoustic features spectrogram
Data augmentation pitch shifting
PDF

Self-Supervised Representation Learning for First-Shot Unsupervised Anomalous Sound Detection

Wang Jiajun, Wang Junjie, Chen Shengbing, Xu Zhiqi, Wan Mengyuan
HFUU, HeFei, China

Abstract

This paper describes a self-supervised representation learning system for the DCASE 2023 Challenge Task 2: "First-shot compliant unsupervised anomaly detection (ASD) for machine condition monitoring".First-shot ASD does not allow systems to do machine-type dependent hyperparameter tuning or tool ensembling based on the performance metric calculated with the grand truth. Due to the challenges in extracting meaningful features from exposure methods of outlier values in anomaly detection, a novel approach of self-supervised representation learning is introduced. The proposed method involves initial classification based on sound metadata, and subsequent feature extraction, and ultimately, anomaly scores are obtained through an anomaly detection algorithm. Our final system is a result of integrating multiple systems together. The proposed system achieves a 63.16% area under the curve (AUC) and partial AUC (p = 0.1) in the harmonized average across all machine types, subsets, and domains on the development dataset.

System characteristics
Classifier CNN, GMM, KNN, LOF, Transformer, ensemble
System complexity 4971030
Acoustic features log-mel energies
Data augmentation smote,mixup
Subsystem count 3
PDF

UNSUPERVISED ABNORMAL SOUND DETECTION SYSTEM BASED ON MULTI-ATTRIBUTE

Chengliang Jiang, Yan Wang
A Fujitsu Company, PFU SHANGHAI Co, Ltd., Shanghai, China and PFU Shanghai Ltd., Shanghai, China

Abstract

This technical report describes submission to DCASE 2023 Task 2. In this report, we propose a multi-attribute training method for anomalous sound detection, which includes feature preprocessing, model training, center loss, triplet loss, and anomaly score selection. The experimental results show that our anomalous sound detection model is superior to the official model.

System characteristics
Classifier CNN
System complexity 1657392, 779992
Acoustic features kaldi.fbank, log-mel energies
Data augmentation pitch shifting
External data usage IDMT-ISA-ELECTRIC-ENGINE
PDF

THUEE SYSTEM FOR FIRST-SHOT UNSUPERVISED ANOMALOUS SOUND DETECTION FOR MACHINE CONDITION MONITORING

Anbai Jiang, Qijun Hou, Jia Liu, Pingyi Fan, Jitao Ma, Cheng Lu, Yuanzhi Zhai, Yufeng Deng, Wei-Qiang Zhang
Department of Electronic Engineering, Tsinghua University, Beijing, China and Tsinghua University, Beijing, China and North China Electric Power University, Beijing, China

Abstract

This report presents our work for DCASE 2023 Task 2: first-shot unsupervised anomalous sound detection for machine condition monitoring. This task mainly focuses on first-shot problems compared with previous challenges. No hyperparameter tuning and developing systems on some machines while testing on other machines bring a lot of challenges. We have developed several kinds of systems to detect first-shot sound anomalies better: training embedding extraction systems from scratch, finetuning pre-trained embedding extractors, and employing normalizing flows. Different kinds of systems give complementary information. We achieve the best hmean of 69.46% on the development set through system fusion.

System characteristics
Classifier NFCDEE, classifier, nfcdee
System complexity 1.206B, 6574848
Acoustic features log-mel energies
Decision making median
System embeddings wav2vec, hubert, unispeech, wavlm
Subsystem count 6
External data usage wav2vec, hubert, unispeech, wavlm
PDF

ANOMALOUS SOUND DETECTION BASED ON SELF-SUPERVISED LEARNING

Wang Junjie, Wang Jiajun, Chen Shengbing, Sun Yong, Liu Mengyuan
IESEFPT, hefei, China and IESEFPT, Hefei, China

Abstract

This technical report presents our approach for Task 2 of the DCASE 2023 Challenge, which focuses on unsupervised anomaly sound detection for machine condition monitoring. We constructed four subsystems, where the first two are based on self-supervised learning methods that utilize feature vectors extracted from convolutional neural networks and employ outlier detection algorithms to identify abnormal sounds. The third subsystem incorporates a modification of the Mahalanobis distance autoencoder (AE) to better adapt to domain shift. The fourth subsystem integrates the previous three systems. The experimental results demonstrate that the proposed system outperforms the baseline significantly on the development set.

System characteristics
Classifier AE, CNN, KNN, cnn, cosine distance, ensemble, smote
System complexity 3010000, 3105433, 3124602, 3135603
Acoustic features log-mel energies, spectrum
Data augmentation mixup
PDF

TWO-STAGE CONTRASTIVE LEARNING FOR ANOMALOUS SOUND DETECTION

Seunghyeon Shin, Seokjin Lee
School of Electronic and Electrical Engineering, Kyungpook National University, Daegu, Korea

Abstract

This technical report describes our anomalous sound detection system submission for DCASE 2023 Task 2. Our system is composed of two stages: a self-supervised contrastive learning network as a feature extractor and a covariance estimator for anomalous scoring. The feature extractor network is trained only once and used across all classes, while the anomalous score is calculated using the mahalanobis distance with the covariance estimator. Our system tested with two kinds of covariance estimation method. Our system with maximum likelihood covariance estimation method achieved a performance improvement of 7.39% and 5.5% over the baseline system which uses mean square error loss and mahalanobis distance loss, based on the official scoring metric of DCASE 2023 Task 2

System characteristics
Classifier contrastive learning, elliptic envelope, maximum likelihook covariance estimator
System complexity 11496000
Acoustic features log-mel spectrogram
Data augmentation pitch shifting, gaussian noise, time masking
PDF

General Anomalous Sound Detection Using Sound Event Classification and Detection

Ying Zeng, Hongqing Liu, Yi Zhou
Chongqing University of Posts and Telecommunications, Chongqing, China

Abstract

This technical report describes our team's submission to DCASE 2023 Task 2. In this report, we utilize sound event classification and detection as an auxiliary task for anomalous sound detection (ASD), and this method only needs to train a general ASD model to detect anomalies, and detects multiple anomalies, and can detect them at the same time. The experimental results show that our ASD model outperforms the official model.

System characteristics
Classifier CNN, ViT
System complexity 3706766, 4192938, 486172
Acoustic features log-mel energies
Decision making average
Subsystem count 2, 4
External data usage pre-trained model
PDF

UNSUPERVISED ANOMALOUS DETECTION BASED ON UNSUPERVISED PRETRAINED MODELS

Zhiqiang Lv, Bing Han, Zhengyang Chen, Yanmin Qian, Jiawei Ding, Jia Liu
Huakong AI Plus, Beijing, China and Shanghai Jiao Tong University, Shanghai, China

Abstract

Unsupervised pretrained models have been widely applied in lots of scenarios successfully. DCASE 2023 challenge Task2 is about first-shot unsupervised anomalous sound detection. To solve this problem, we tried to use several unsupervised pretrained models trained on thousands hours of speech. By fine-tuning pretrained big models with datasets of DCASE 2023 challenge Task2, we found that pretrained models outperformed small models trained from scratch. Our best pretrained model achieve hmean of 63.84% on the development dataset, which is much better than the auto-encoder baseline.

System characteristics
Classifier Transformer
System complexity 300000000
Acoustic features raw waveform
Decision making median
System embeddings wav2vec2, wav2vec2, hubert, unispeech, wavlm, wav2vec2, unispeech, wavlm
Subsystem count 3, 4, 6
External data usage wav2vec2, wav2vec2, unispeech, wavlm
PDF

ENSEMBLE SYSTEMS WITH GAN AND AUTO-ENCODER MODELS FOR ANOMALOUS SOUND DETECTION

Zhonghao Zhao, Yang Tan, Kun Qian, Kele Xu, Bin Hu
(1) Ministry of Education (Beijing Institute of Technology) (2) Beijing Institute of Technology, (1) Key Laboratory of Brain Health Intelligent Evaluation and Intervention (2) School of Medical Technology, P.R. China and (1) Key Laboratory of Brain Health Intelligent Evaluation and Intervention (2) School of Medical Technology, P.R. China and National University of Defense Technology, Changsha, P.R. China

Abstract

In this paper, we describe our submissions for DCASE 2023 Challenge Task 2. For solving anomalous sound detection problem, an ensemble system with gan and auto-encoder model are proposed. Spectrograms and log-mel energies are used to train models. As a result, the proposed systems achieved a better performance than the baseline models.

System characteristics
Classifier AE, GAN
System complexity 269992
Acoustic features log-mel energies, spectrogram
PDF

ANOMALOUS SOUND DETECTION USING CNN-BASED MODELS AND ENSEMBLE

Ryosuke Tanaka, Keisuke Ikeda, Shiya Aoyama, Satoshi Tamura
Gifu University, Gifu, Japan and Gifu, Gifu, Japan

Abstract

This paper presents our efforts for DCASE2023 Challenge Task2. We explore three schemes: (1) sound anomaly detection based on state-of-the-art image processing techniques with machine type classifiers, (2) anomaloous detection based on the same image processing in addition to the inpainting strategy, (3) anomaly detection utilizing machine setting classification to enhance the performance, and (4) anomaly detection by composing existing detectors in the ensemble manner. Experiments were conducted to evaluate our approaches.

System characteristics
Classifier AE, CNN, Mahalanobis distance, ensemble
System complexity 11234503, 11365312, 2,062,744
Acoustic features log-mel energies, log-mel spectrogram
Data augmentation frequency masking, time masking, gaussian noise, gaussian noise, streching
Subsystem count 7
PDF

Fraunhofer FKIE submission for Task 2: First-Shot Unsupervised Anomalous Sound Detection for Machine Condition Monitoring

Kevin Wilkinghoff
Communication Systems, Fraunhofer FKIE, Wachtberg, Germany

Abstract

This report contains a description of the Fraunhofer FKIE submission for task 2 "First-Shot Unsupervised Anomalous Sound Detection for Machine Condition Monitoring" of the DCASE challenge 2023. The submitted system is an adaptation of a previously proposed embedding model for extracting representations of audio data suitable for detecting anomalous sounds in domain shifted conditions. The model consists of two sub-models utilizing static and dynamic frequency information and is trained through an auxiliary classification task using the sub-cluster AdaCos loss. In this work, a modified version of mixup is presented and shown to improve the performance, especially increasing the partial area under the receiver operating characteristic curve. As a result, the proposed system is shown to significantly outperform both baseline systems of the challenge.

System characteristics
Classifier CNN, ensemble
System complexity 34417490, 42036050, 76453540
Acoustic features magnitude spectrogram, magnitude spectrum
Data augmentation mixup
Decision making average, maximum, sum
Subsystem count 10, 20
PDF

ANOMALOUS SOUND DETECTION SYSTEM WITH GAN AND AE FOR DCASE2023 CHALLENGE TASK 2

Tianxin Wu
Suzhou Qimengzhe Technology Company, Co., Ltd., Suzhou, China

Abstract

This report describes the system for DCASE 2023 Challenge Task 2, which aims to detect anomalous machine states through sound using machine learning methods, where the training dataset itself does not contain any anomalous examples. We constructed a method based on Generative Adversarial Networks (GAN). The system achieved the best score of 86.20% on the development dataset for the machine type "slider," while the corresponding baseline score based on autoencoders was 69.06% and 83.18%.

System characteristics
Classifier AE, CNN, GAN
System complexity 269992
Acoustic features log-mel spectrogram
External data usage simulation of anomalous samples
Front end system PCA
PDF

UNSUPERVISED ABNORMAL SOUND DETECTION BASED ON FEATURE FUSION IN FIRST-SHOT CONDITION

Yao Xiao, Tao Peng, Shi Feng, Yanli Wang, Hao Ba, Chenyang Zhu, Shengchen Li, Xi Shao
Telecommunications & Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, China and SAMSUNG Electronics (China) R&D Centra, Nanjing, China and School of Advanced Technology, Suzhou, China and Telecommunications & Information Engineering, Nanjing, China

Abstract

The DCASE2023 Challenge Task2 is to develop an unsupervised detection system of anomalous sounds for seven types of machines under first shot conditions. In this paper, we use a novel feature fusion way as the system input, using two simple models: one is Autoencoder(AE) and another is GMM. It shows that our feature fu- sion has significantly improved the results compared with the base- line in general, especially the GMM.

System characteristics
Classifier AE, CNN, GMM
System complexity 0, 221809, 713910
Acoustic features log-mel, spectral coherence, wavelet
PDF

UNSUPERVISED LEARNING FOR ANOMALOUS SOUND DETECTION BASED ON PREDICTION AND RECONSTRUCTION TASKS

Fengrun Zhang, Chenguang Hu, Kai Guo
School of Information and Electronics, Beijing Institute of Technology, Beijing, China and Beijing Institute of Technology, Beijing, China

Abstract

The purpose of anomalous sound detection is to detect whether the sound emitted by the machine is normal or anomalous. Due to the scarcity and diversity of anomalous data, only normal audio data is used to detect anomalies. The DCASE 2023 challenge is dedicated to developing a general-purpose anomalous detection algorithm that has good anomalous detection results on different machine types. For the problem scenario of DCASE 2023, we have developed four systems for anomalous sound detection, which are called VIDNN, CPC-VAE, VAE-GMM, DDPM.

System characteristics
Classifier CNN, Contrastive Learning, Denoising Diffusion Probability Model, GMM, VAE
System complexity 229948, 35704705
Acoustic features STFT spectrum, log-mel energies
PDF

Anomalous Sound Detection via Multitask Learning and Adversarial Learning

Yucong Zhang, Ming Li
Data Science Research Center, Duke Kunshan University, Suzhou, China and Duke Kunshan University, Suzhou, China

Abstract

This technical report describes our submitted systems to DCASE 2023 Challenge Task 2. We propose two different methods. The first one is a multitask learning method, which incorporates a self-supervised attribute classification and a GMM-based scoring. The second one is to directly train an anomaly evaluator via adversarial learning, which achieves domain generalization by learning inherit properties other than the attributes. Experimental results on the development dataset show that both our methods outperform the baseline methods. The ensemble system has an average improvement of 8% based on the baseline results.

System characteristics
Classifier CNN, GMM, VAE, conformer
System complexity 1.3M, 10.53M, 12.91M, 24.74M
Acoustic features log-mel spectrogram, raw waveform
Data augmentation mixup,pitch shifting,time stretching,gaussian noise,fading,time shifting,time masking,frequency masking
Decision making average
Subsystem count 3
PDF

Attribute Classifier with Imbalance Compensation for Anomalous Sound Detection

Yifan Zhou, Yanhua Long
Shanghai Normal University, Shanghai, China

Abstract

This paper proposes an Attribute Classifier with Imbalance Compensation (ACIC) for DCASE 2023 Challenge Task 2. The goal is to perform anomalous sound detection by exploiting prior knowledge about machine attributes. First, we propose to use the weak prior knowledge provided by attribute for anomaly detection. Then, we design the Imbalance Compensation (IC) strategy to address the class imbalance problem of attributes. Finally, we propose a score fusion method based on ACIC to enhance the robustness of the model. Experimental results show that compensating for attribute class imbalance improves the exposure of anomalies.

System characteristics
Classifier AE, KNN, ResNet
System complexity 11171280, 269992
Acoustic features log-mel energies
Data augmentation gaussian noise, time stretching, pitch shifting, shifting
Subsystem count 2
PDF