@techreport{jung_cmu_t6_2024,
    author = "Jung, Jee-weon and Zhang, Dong and Yang, Huck C.-H. and Wu, Shih-Lun and Chan, David M. and Kong, Zhifeng and Ruifan, Deng and Yaqian, Zhou and Rafael, Valle and Watanabe, Shinji",
    title = "AUTOMATIC AUDIO CAPTIONING WITH ENCODER FUSION, MULTI-LAYER AGGREGATION, AND LARGE LANGUAGE MODEL ENRICHED SUMMARIZATION",
    institution = "DCASE2024 Challenge",
    year = "2024",
    month = "May",
    abstract = "In this report, we describe our submission to Track 6 of the DCASE 2024 challenge for the task of Automated Audio Captioning (AAC). The submitted models utilize an encoder-decoder architecture using pre-trained and frozen audio encoders, a Conformer post-encoder, and a BART decoder. We introduce five different architectures, employing diverse fusion strategies to leverage multiple audio encoders and a multi-layer aggregation technique, thus exploiting the complementary information from various representations. For inference, we propose a novel scheme incorporating nucleus sampling, CLAP-based filtering, hybrid re-ranking, and large language model summarization. Combining these approaches, our top-performing single and ensemble systems achieve Fluency Enhanced Sentence-BERT Evaluation (FENSE) scores of 0.5410 and 0.5442, respectively, on the Clotho (V2) evaluation partition.",
    url = "https://dcase.community/documents/challenge2024/technical\_reports/DCASE2024\_Jung\_74\_t6.pdf",
    note = "Ranked 1/12 in the DCASE2024 Challenge Task 6 with FENSE score of 0.554."
}

@techreport{kim_snu_t6_2024,
    author = "Kim, Jaeyeon and Jung, Jaeyoon and Jeon, Minjeong and Woo, Sang Hoon and Lee, Jinjoo",
    title = "Expanding on EnCLAP with Auxiliary Retrieval Model for Automated Audio Captioning",
    institution = "DCASE2024 Challenge",
    year = "2024",
    month = "May",
    abstract = "In this technical report, we describe our submission to DCASE2024 Challenge Task6 (Automated Audio Captioning) and Task8 (Language-based Audio Retrieval). We develop our approach building upon the EnCLAP audio captioning framework and optimizing it for Task 6 of the challenge. Notably, we outline the changes in the underlying components and the incorporation of the reranking process. Additionally, we submit a supplementary retriever model, a byproduct of our modified framework, to Task8. Our proposed systems achieve FENSE score of 0.542 on Task6 and mAP@10 score of 0.386 on Task8, significantly outperforming the baseline models.",
    url = "https://dcase.community/documents/challenge2024/technical\_reports/DCASE2024\_Kim\_108\_t6.pdf",
    note = "Ranked 2/12 in the DCASE2024 Challenge Task 6 with FENSE score of 0.544."
}

@techreport{chen_sjtu_t6_2024,
    author = "Chen, Wenxi and Li, Xiquan and Ma, Ziyang and Liang, Yuzhe and Jiang, Anbai and Zheng, Zhisheng and Qian, Yanmin and Fan, Pingyi and Zhang, Wei-Qiang and Lu, Cheng and Liu, Jia and Chen, Xie",
    title = "SJTU-THU Automated Audio Captioning System for DCASE 2024",
    institution = "DCASE2024 Challenge",
    year = "2024",
    month = "May",
    abstract = "Task 6 (Automated Audio Captioning) of the DCASE 2024 Challenge requires the automatic creation of textual descriptions for general audio signals. This technical report presents a novel model that integrates a self-supervised model with a large language model (LLM) for audio captioning. For audio feature extraction, we utilize the efficient self-supervised pre-trained model, EAT, to achieve more effective audio representation extraction. The language model component is based on Vicuna, a large language model, which we fine-tune using LoRA to fully harness its robust reasoning capabilities. During training, linear layers function as projectors to align audio and textual representations. Our model is pre-trained using the Clotho, WavCaps, AudioCaps, and MACS datasets, and fine-tuned on Clotho. For decoding, we employ a filtering strategy based on the CLAP model. By leveraging the text-audio alignment capabilities of the CLAP model, we filter out the beam search decoding results to retain only the textual description that best matches the input audio. Evaluation on the testing subset of Clotho demonstrates that our model achieves a FENSE score of 0.5431 in the single-system setting and 0.5429 in the multi-system setting, while the multi-systems outperform the single-system in other metrics. Our project code is based on the SLAM-LLM toolkit.",
    url = "https://dcase.community/documents/challenge2024/technical\_reports/DCASE2024\_Chen\_2\_t6.pdf",
    note = "Ranked 3/12 in the DCASE2024 Challenge Task 6 with FENSE score of 0.541."
}

@techreport{li_alxc_t6_2024,
    author = "Liu, Jizhong and Li, Gang",
    title = "Leveraging CED Encoder and Large Language Models for Automated Audio Captioning",
    institution = "DCASE2024 Challenge",
    year = "2024",
    month = "May",
    abstract = "This technical report presents an automated audio captioning (AAC) method participating in the DCASE 2024 Challenge Task 6. The method builds upon our previous work.Recent advancements in large language models (LLMs), coupled with improved training approaches for audio encoders, have opened up possibilities for enhancing AAC. Thus, we optimize AAC from three points: 1) a pre-trained audio encoder named consistent ensemble distillation (CED) improves the effectivity of acoustic tokens, with a querying transformer (Q-Former) bridging the modality gap to LLM and compress acoustic tokens; 2) we introduce a Llama 2 with 7B parameters as the decoder; 3) a frozen Llama 3 Instruct with 8B parameters corrects text errors caused by insufficient training data and annotation ambiguities. Both the encoder and text decoder are optimized by low-rank adaptation (LoRA). Our method obtains a 53.2 FENSE score.",
    url = "https://dcase.community/documents/challenge2024/technical\_reports/DCASE2024\_Li\_42\_t6.pdf",
    note = "Ranked 4/12 in the DCASE2024 Challenge Task 6 with FENSE score of 0.533."
}

@techreport{kyogu_snu_t6_2024,
    author = "Eungbeom, Kim and Jaeheon, Sim and Woo, Lee Jin and Kyogu, Lee",
    title = "Retrieval-Augmented Audio Captioning with LLM fine-tuning",
    institution = "DCASE2024 Challenge",
    year = "2024",
    month = "May",
    abstract = "This technical report introduces an audio captioning system, which is designed to tackle the task of Automated Audio Captioning(AAC) in the Detection and Classification of Acoustic Scenes and Events (DCASE) 2024 challenge. Our approach employs BEATs for robust audio representation learning and Llama 3 for high-quality text generation. To address the limitations of small datasets like Clotho, we fix the pre-trained weights of the BEATs and train a small linear model to map audio encoder dimensions to the LLM input. We further fine-tune the LLM using parameter-efficient fine-tuning method, LoRA, to train the model. We also explore the con-catenation based LoRA merging method, achieving notable results on standard benchmarks. Experimental results show that our proposed system achieves a FENSE [1] score of 0.5180 on the evaluation dataset.",
    url = "https://dcase.community/documents/challenge2024/technical\_reports/DCASE2024\_Kyogu\_111\_t6.pdf",
    note = "Ranked 5/12 in the DCASE2024 Challenge Task 6 with FENSE score of 0.526."
}

@techreport{kong_cuhk_t6_2024,
    author = "Feng, Qianhang and Kong, Qiuqiang",
    title = "Semantic Enhancement Encoder for Audio Captioning and Spectrogram-based data augmentation",
    institution = "DCASE2024 Challenge",
    year = "2024",
    month = "May",
    abstract = "Automatic Audio Captioning (AAC) is a process that transforms audio signals into descriptive narratives. This paper introduces an innovative automated audio captioning model developed for the Detection and Classification of Acoustic Scenes and Events (DCASE) 2024 Challenge Task 6A. The model architecture presented here is meticulously designed to adeptly manage the intricacies of AAC tasks. Additionally, this project introduces a novel data enhancement technique, which, with minimal model adjustments, significantly boosts performance. Exclusively trained and fine-tuned on the Clotho dataset, this project achieved a final SPIDEr-FL score of 0.3318, demonstrating its effectiveness.",
    url = "https://dcase.community/documents/challenge2024/technical\_reports/DCASE2024\_Kong\_10\_t6.pdf",
    note = "Ranked 6/12 in the DCASE2024 Challenge Task 6 with FENSE score of 0.525."
}

@techreport{choi_kaist_t6_2024,
    author = "Choi, Inhan and Nam, Hyeonuk and Min, Deokki and Choi, Seung-Deok and Park, Yong-Hwa",
    title = "Self Training and Ensembling Frequency Dependent Networks with Coarse Prediction Pooling and Sound Event Bounding Boxes",
    institution = "DCASE2024 Challenge",
    year = "2024",
    month = "May",
    abstract = "To tackle sound event detection (SED) task, we propose frequency dependent networks (FreDNets), which heavily leverage frequency-dependent methods. We apply frequency warping and FilterAugment, which are frequency-dependent data augmentation methods. The model architecture consists of 3 branches: audio teacher-student transformer (ATST) branch, BEATs branch and CNN branch including either partial dilated frequency dynamic convolution (PDFD) or squeeze-and-Excitation (SE) with time-frame frequency-wise SE (tfwSE). To train MAESTRO labels with coarse temporal resolution, we apply max pooling on prediction for the MAESTRO dataset. Using best ensemble model, we apply self training to obtain pseudo label from DESED weak set, DESED unlabeled set and AudioSet. AudioSet labels are filtered to focus on high-confidence pseudo labels and AudioSet pseudo labels are used to train on DESED labels only. We used change-detection-based sound event bounding boxes (cSEBBs) as post processing for ensemble models on self training and submission models.",
    url = "https://dcase.community/documents/challenge2024/technical\_reports/DCASE2024\_Choi\_38\_t6.pdf",
    note = "Ranked 7/12 in the DCASE2024 Challenge Task 6 with FENSE score of 0.520."
}

@techreport{li_scut_t6_2024,
    author = "Li, Qianqian",
    title = "SCUT SUBMISSION FOR AUTOMATED AUDIO CAPTIONING USING GRAPH ATTENTION AND CROSS-ATTENTION MECHANISMS",
    institution = "DCASE2024 Challenge",
    year = "2024",
    month = "May",
    abstract = "This report presents our work for automated audio caption-ing which is the Task 6A of DCASE 2024. Our system is an encoder-decoder framework. The encoder uses a pre-trained ConvNeXt network and the decoder employs a standard Transformer structure. Among the encoders, we include a graph attention module to enhance the module's ability to extract audio features. In the decoder, in addition to the Transformer's multi-head self-attention mechanism, a cross-attention mechanism is added to improve the association between output subtitles and audio features. Finally, our system achieves FENSE score of 0.5131 which is higher than the baseline system's FENSE score of 0.5040.",
    url = "https://dcase.community/documents/challenge2024/technical\_reports/DCASE2024\_Li\_54\_t6.pdf",
    note = "Ranked 8/12 in the DCASE2024 Challenge Task 6 with FENSE score of 0.520."
}

@techreport{de_jesus_silva_jkuicp_t6_2024,
    author = "Silva, Jakob De Jesus and Tobias, Justus and Sonderegger, Sebastian",
    title = "HYPERPARAMETER TUNING OF THE CONETTE AUDIO CAPTIONING SYSTEM",
    institution = "DCASE2024 Challenge",
    year = "2024",
    month = "May",
    abstract = "In the course of this challenge, we explored various methods to achieve a state-of-the-art audio captioning model. Initially, we worked with the baseline provided by the challenge organizers, then we also constructed several models from scratch, using diverse ar- chitectures. The best outcome we could achieve, was by tuning the hyperparameters of the baseline model CoNeTTE[1]. Our system- atic approach involved finding hyperparameters that had the most effect on performance and their best combination. Although our enhanced baseline model demonstrated some performance gains, it still did not achieve a significant breakthrough over the original baseline. This is a student project in course of the lecture ”Machine- learning and Audio: A Challenge” at JKU.",
    url = "https://dcase.community/documents/challenge2024/technical\_reports/DCASE2024\_De Jesus Silva\_60\_t6.pdf",
    note = "Ranked 9/12 in the DCASE2024 Challenge Task 6 with FENSE score of 0.516."
}

@techreport{epshtein_arc_t6_2024,
    author = "Epshtein, Dan and Amsalem, Yuval and Amar, Alon",
    title = "DCASE 2024 TASK6: AUTOMATED AUDIO CAPTIONING USING CONTRASTIVE LEARNING",
    institution = "DCASE2024 Challenge",
    year = "2024",
    month = "May",
    abstract = "This technical report presents our proposed enhancements to improving the baseline results of the DCASE2024 challenge Task 6 on Automated Audio Captioning. We introduce an additional loss function for contrastive learning, incorporating the NTXent loss as proposed in [1][3] into the baseline platform.",
    url = "https://dcase.community/documents/challenge2024/technical\_reports/DCASE2024\_Epshtein\_34\_t6.pdf",
    note = "Ranked 10/12 in the DCASE2024 Challenge Task 6 with FENSE score of 0.514."
}

@techreport{hong_cau_t6_2024,
    author = "Hong, Hyunhee and Lee, Yunjung",
    title = "DCASE 2024 task 6 automated audio captioning",
    institution = "DCASE2024 Challenge",
    year = "2024",
    month = "May",
    abstract = "This project describes an Automated Audio Captioning model for the Detection and Classification of Acoustic Scenes and Events (DCASE) 2024 Challenge, Task 6. The proposed systems in this submission are based on a supervised language-audio pretraining strategy. Experiments show that our systems can achieve a SPIDEr-FL score of 29.39 on automated audio captioning.",
    url = "https://dcase.community/documents/challenge2024/technical\_reports/DCASE2024\_Hong\_16\_t6.pdf",
    note = "Ranked 11/12 in the DCASE2024 Challenge Task 6 with FENSE score of 0.513."
}