@techreport{Akiyama2019,
    Author = "Akiyama, Osamu and Sato, Junya",
    title = "MULTITASK LEARNING AND SEMI-SUPERVISED LEARNING WITH NOISY DATA FOR AUDIO TAGGING",
    institution = "DCASE2019 Challenge",
    year = "2019",
    month = "June",
    abstract = {This paper describes our submission to the DCASE 2019 challenge Task 2 "Audio tagging with noisy labels and minimal supervision" [1]. This task is a multi-label audio classification with 80 classes. The training data is composed of a small amount of reliably labeled data (curated data) and a larger amount of data with unreliable labels (noisy data). Additionally, there is a difference between data distribution between curated data and noisy data. To tackle this difficulty, we propose three strategies. The first is multitask learning using noisy data. The second is semi-supervised learning (SSL) using input data with a different distribution from labeled input data. The third is an ensemble method that averages models learned with different time windows. By using these methods, we achieved a score of 0.750 with label-weighted label-ranking average precision (lwlrap), which is in the top 1\% on the public leaderboard (LB).}
}

@techreport{Boqing2019,
    Author = "Boqing, Zhu and Kele, Xu and Dezhi, Wang and ACHE, Mathurin",
    title = "MULTI-LABEL AUDIO TAGGING WITH NOISY LABELS AND VARIABLE LENGTH",
    institution = "DCASE2019 Challenge",
    year = "2019",
    month = "June",
    abstract = "This paper describes our approach for DCASE 2019 Task2: Audio tagging with noisy labels and minimal supervision. This challenge uses a smaller set of manually labeled data and a larger set of noise-labeled data to enable the system to perform multi-label audio tagging tasks with minimal supervision conditions. We aim to tagging the audio clips with convolutional neural network under a limited computation and storage resources. To tackle the problem of noisy label data, we propose a data generation method named Dominate Mixup. It can restrain the impact of incorrect label during back propagation and it’s suitable for multi-class classification problem. In response to the variable length of audio clips, we conduct an efficient learning method with cyclical audio length which allow us to learn more pattern from widely diverse sound events. On the public leaderboard for the competition, our single model and simple ensemble of 5 models score 0.711 and 0.725 respectively."
}

@techreport{Bouteillon2019,
    Author = "Bouteillon, Eric",
    title = "SPECMIX: A SIMPLE DATA AUGMENTATION TO LEVERAGE CLEAN AND NOISY SET FOR EFFICIENT AUDIO TAGGING",
    institution = "DCASE2019 Challenge",
    year = "2019",
    month = "June",
    abstract = "This paper presents a semi-supervised warm-up pipeline used to create an efficient audio tagging system as well as a novel data augmentation technique for multi-labels audio tagging named by the author SpecMix. These new techniques were applied to our submitted audio tagging system to the Freesound Audio Tagging 2019 challenge carried out within the DCASE 2019 Task 2 challenge [3]. Purpose of this challenge consist of predicting the audio labels for every test clips using machine learning techniques trained on a small amount of reliable, manually-labeled data, and a larger quantity of noisy web audio data in a multi-label audio tagging task with a large vocabulary setting."
}

@techreport{Ebbers2019,
    Author = "Ebbers, Janek and Haeb-Umbach, Reinhold",
    title = "CONVOLUTIONAL RECURRENT NEURAL NETWORK AND DATA AUGMENTATION FOR AUDIO TAGGING WITH NOISY LABELS AND MINIMAL SUPERVISION",
    institution = "DCASE2019 Challenge",
    year = "2019",
    month = "June",
    abstract = "This report presents our Audio Tagging system for the DCASE 2019 Challenge Task 2. Our proposed neural network architecture consists of a convolutional front end using log-mel-energies as input features, a recurrent neural network sequence encoder outputting a single vector for a whole sequence and finally a fully connected classifier network outputting an activity probability for each of the 80 event classes. Due to the limited amount of available data we use various data augmentation techniques to prevent overfitting and improve generalization. Our best system achieves a label-weighted label-ranking average precision (lwlrap) of 73.0\% on the public test set which is an absolute improvement of 19.3\% over the baseline."
}

@techreport{Fonseca2019,
    Author = "Fonseca, Eduardo and Font, Frederic and Plakal, Manoj and Ellis, Daniel P. W.",
    title = "AUDIO TAGGING WITH NOISY LABELS AND MINIMAL SUPERVISION",
    institution = "DCASE2019 Challenge",
    year = "2019",
    month = "June",
    abstract = "This paper introduces Task 2 of the DCASE2019 Challenge, titled “Audio tagging with noisy labels and minimal supervision”. This task was hosted on the Kaggle platform as “Freesound Audio Tagging 2019”. The task evaluates systems for multi-label audio tagging using a large set of noisy-labeled data, and a much smaller set of manually-labeled data, under a large vocabulary setting of 80 everyday sound classes. In addition, the proposed dataset poses an acoustic mismatch problem between the noisy train set and the test set due to the fact that they come from different web audio sources. This can correspond to a realistic scenario given by the difficulty of gathering large amounts of manually labeled data. We present the task setup, the FSDKaggle2019 dataset prepared for this scientific evaluation, and a baseline system consisting of a convolutional neural network. All these resources are freely available."
}

@techreport{Hong2019,
    Author = "Hong, Xiaofeng and Liu, Gang",
    title = "MULTI-LABEL AUDIO TAGGING SYSTEM FOR FREESOUND 2019: FOCUSING ON NETWORK ARCHITECTURES, LABEL NOISY AND LOSS FUNCTIONS",
    institution = "DCASE2019 Challenge",
    year = "2019",
    month = "June",
    abstract = "In this technical report, we propose our solutions applied to our submission for DCASE2019 Task2. We focus on the model architectures which can efficiently tag the audio with multi-label and noisy label. Furthermore, we use multi-label models based on convolutional network and recurrent network to unify detection of audio events. Graph representation is also utilized to take the audio event co-occurrence into account which is reflected in the loss functions. We also tried Semi-Supervised Learning to use the noisy data. Finally, we tried an ensemble of CNNs and CRNN, trained by using cross validation folds. Compared to the baseline score of 0.537, we achieved a score of 0.700 on the public leaderboard."
}

@techreport{Kharin2019,
    Author = "Kharin, Alexander",
    title = "DCASE 2019 CHALLENGE NOISY\_ANNEALING SYSTEM TECHNICAL REPORT",
    institution = "DCASE2019 Challenge",
    year = "2019",
    month = "June",
    abstract = "Multy-layer convolutional neural network with following Dense layer with 4.7 millions of parameters was used for training on mel-spectrograms of audio data. Such large number of parameters and small dataset (\textasciitilde 9k samples without augumentation) leads to vulnerability of model to overfitting. Agumentation of audiofiles (i.e cropping of spectrograms) was not found wery effective way to get rid of overfitting. The following ways found to be reasonoble: standard Kfold technique with training on 5 Kfolds and averaging of the results and so-called ‘noisy data annealing’. That method lies on sequential training of the model on general set for several epochs (30 in our case) followed by training on poorly labeled, but larger dataset for 5 epochs. After several cycles we can observe significant reduction of the overfitting (lwrap scores 0.61 for base model, 0.66 for noisydata-annealed model). Such increase is caused by partial ‘reset’ of the trainable parameters during training on poorly-labelled set. The more set-specific parameters are, the higher is ‘reset’ rate, so such annealing enhances the significance of non-overfitting-responsible features and reduces the impact of highly dataset-specific features."
}

@techreport{Kong2019,
    Author = "Kong, Qiuqiang and Cao, Yin and Iqbal, Turab and Wang, Wenwu and Plumbley, Mark D.",
    title = "CROSS-TASK LEARNING FOR AUDIO TAGGING, SOUND EVENT DETECTION AND SPATIAL LOCALIZATION: DCASE 2019 BASELINE SYSTEMS",
    institution = "DCASE2019 Challenge",
    year = "2019",
    month = "June",
    abstract = "The Detection and Classification of Acoustic Scenes and Events (DCASE) 2019 challenge focuses on audio tagging, sound event detection and spatial localisation. DCASE 2019 consists of five tasks: 1) acoustic scene classification, 2) audio tagging with noisy labels and minimal supervision, 3) sound event localisation and detection, 4) sound event detection in domestic environments, and 5) urban sound tagging. In this paper, we propose generic cross-task baseline systems based on convolutional neural networks (CNNs). The motivation is to investigate the performance of a variety of models across several audio recognition tasks without exploiting the specific characteristics of the tasks. We looked at CNNs with 5, 9, and 13 layers, and found that the optimal architecture is taskdependent. For the systems we considered, we found that the 9-layer CNN with average pooling after convolutional layers is a good model for a majority of the DCASE 2019 tasks."
}

@techreport{Koutini2019,
    Author = "Koutini, Khaled and Eghbal-zadeh, Hamid and Widmer, Gerhard",
    title = "CP-JKU SUBMISSIONS TO DCASE’19: ACOUSTIC SCENE CLASSIFICATION AND AUDIO TAGGING WITH RECEPTIVE-FIELD-REGULARIZED CNNS",
    institution = "DCASE2019 Challenge",
    year = "2019",
    month = "June",
    abstract = "In this report, we detail the CP-JKU submissions to the DCASE2019 challenge Task 1 (acoustic scene classification) and Task 2 (audio tagging with noisy labels and minimal supervision). In all of our submissions, we use fully convolutional deep neural networks architectures that are regularized with Receptive Field (RF) adjustments. We adjust the RF of variants of Resnet and Densenet architectures to best fit the various audio processing tasks that use the spectrogram features as input. Additionally, we propose novel CNN layers such as Frequency-Aware CNNs, and new noise compensation techniques such as Adaptive Weighting for Learning from Noisy Labels to cope with the complexities of each task. We prepared all of our submissions without the use of any external data. Our focus in this year’s submissions is to provide the best-performing single-model submission, using our proposed approaches."
}

@techreport{Liu2019,
    Author = "Liu, Yanfang and Wei, Qingkai",
    title = "STACKED CONVOLUTIONAL NEURAL NETWORKS FOR AUDIO TAGGING WITH NOISE LABELS",
    institution = "DCASE2019 Challenge",
    year = "2019",
    month = "June",
    abstract = "This technical report describes the system we used to participate in task 2 of the DCASE 2019 challenge. The task is to predict the tags of audio recordings with using a small number of manually-verified labels and a much larger number of noisy labels. In this task, we propose serveral convolutional neural networks to learn from log-mel spectrogram features. To improve the performance, different techniques preprocessing, data augmentations, loss functions and cross-validation are involved. The prediction results are then ensembled using geometric mean. On the test set used for evaluation, our system achieved a score of 0.734."
}

@techreport{Paischer2019,
    Author = "Paischer, Fabian and Prinz, Katharina and Widmer, Gerhard",
    title = "AUDIO TAGGING WITH CONVOLUTIONAL NEURAL NETWORKS TRAINED WITH NOISY DATA",
    institution = "DCASE2019 Challenge",
    year = "2019",
    month = "June",
    abstract = "This report is a description of our submission to the 2019 DCASE Challenge, Task 2. The task at hand is to predict one or more audiotags, out of the 80 available tags, for the audio clips of different lengths, originating from two different datasets. For training, a total number of 4970 audio clips is provided with trustworthy labels, whereas 19815 samples contain a substantial amount of label noise with unknown noise ratio. To tackle this task, we propose two different convolutional neural network (CNN) architectures trained on different features to capture different aspects of the data. Stochastic Weight Averaging is used in order to improve generalisation. By averaging over the predictions of all five networks, we obtain an ensemble that provides us with the likelihood of 80 different labels being present in an input audio clip. On the unseen data of the Public Kaggle Leaderboard, our system reaches a Label Weighted Label Ranking Average Precision (Lwlrap) of 0.722."
}

@techreport{Sun2019,
    Author = "He, Jun and Rao, Penghao and Sun, Bo and Yu, Lejun",
    title = "Audio Tagging with Minimal Supervision Based on Mean Teacher for DCASE 2019 Challenge",
    institution = "DCASE2019 Challenge",
    year = "2019",
    month = "June",
    abstract = "In this report, we describe the mean teacher based audio tagging system and performance applied to the task 2 of DCASE 2018 challenge, where the task evaluates systems for audio tagging with noisy labels and minimal supervision. The proposed system is based on a VGG16 network with attention mechanism and gated CNN. Following data augmentation techniques are used to increase model robustness: a) Scaling the signal with 0.75 to 1.5 time, b) Adding Gaussian white noise with 20dB to 40dB. Samples with noisy labels are regarded as unlabeled and are utilized with semi-supervision method namely mean teacher. The proposed system is trained using 5-fold cross-validation, and the final result is the arithmetic mean of the five models. Finally, the method provides lwlrap score of 0.631, which is measured through the Kaggle platform."
}

@techreport{Zhang2019,
    Author = "He, Kexin and Shen, Yuhan and Zhang, Weiqiang",
    title = "THUEE SYSTEM FOR DCASE 2019 CHALLENGE TASK 2",
    institution = "DCASE2019 Challenge",
    year = "2019",
    month = "June",
    abstract = "In this report, we described our submission for the task 2 of Detection and Classification of Acoustic Scenes and Events (DCASE) 2019 Challenge: Audio tagging with noisy labels and minimal supervision. Our methods are mainly based on two types of deep learning models: Convolutional Recurrent Neural Network (CRNN) and DenseNet. In order to prevent overfitting, we adopted data augmentation using mixup strategy and SpecAugment. Besides, we designed a staged loss function to train our models using both curated and noisy data. We also used various acoustic features, including log-mel energies and perceptual Constant-Q transform (p-CQT), and tried an ensemble of multiple subsystems to enhance the generalization capability of our system. Our final system achieved a lwlrap score of 0.742 on the public leaderboard in Kaggle."
}

@techreport{Zhang2019b,
    Author = "Zhang, Jihang and Wu, Jie",
    title = "DCASE 2019 TASK 2: SEMI-SUPERVISED NETWORKS WITH HEAVY DATA AUGMENTATIONS TO BATTLE AGAINST LABEL NOISE IN AUDIO TAGGING TASK",
    institution = "DCASE2019 Challenge",
    year = "2019",
    month = "June",
    abstract = "This technical report describes a system used for DCASE 2019 Task 2: Audio tagging with noisy labels and minimal supervision. Building a large-scale multi-label dataset normally requires extensive amount of manual effort, especially for general-purpose audio tagging system. To tackle the problem, we use a semi-supervised teacher-student convolutional neural network (CNN) to leverage substantial noisy labels and small curated labels in dataset. To further regularize the system, we exploit multiple data augmentation methods, including SpecAugment [1], mixup [2], and an innovative time reversal augmentation approach. Moreover, a combination of binary Focal [3] and ArcFace [4] losses are used to increase the accuracy of pseudo labels produced by the semi-supervised network, and accelerate the training process. Aadaptive test time augmentation (TTA) based on the lengths of audio samples is used as a final approach to improve the system. We choose a single system that generates the submission file Zhang BIsmart task2 3.output.csv to be the candidate model considered for the Judges’ Award. Other two systems use ensemble approach to furthur improve the performance."
}