@techreport{Agafonov2018,
    Author = "Agafonov, Iurii and Shuranov, Evgeniy",
    title = "AUDIO TAGGING USING LABELED DATASET WITH NEURAL NETWORKS",
    institution = "DCASE2018 Challenge",
    year = "2018",
    month = "September",
    abstract = "In this paper, an audio tagging system is proposed. This system uses fusion of 5 Convolutional Neural Network (CNN) and 1 Convolutional Recurrent Neural Network (CRNN) classifiers in attempt to achieve better results. The proposed system reaches 0.95 score in public leaderboard."
}

@techreport{Chakraborty2018,
    Author = "Chakraborty, Ria",
    title = "DIVERSIFIED SYSTEM OF DEEP CONVOLUTIONAL NEURAL NETWORKS WITH STACKED SPECTRAL FUSION FOR AUDIO TAGGING",
    institution = "DCASE2018 Challenge",
    year = "2018",
    month = "September",
    abstract = "This paper outlines a diversified system of deep convolutional neural networks with stacked fusion of spectral features for the DCASE 2018 Task 2 [1], freesound general-purpose audio tagging. The primary objective of this research has been to develop a solution which can churn out decent performance and be deployed within reasonable resource constraints. The two best performing submissions are the results of only two and three different CNNs, with their results being combined based on a boosted tree algorithm with fused spectral features. This paper describes the submissions which are made under the team name Gyat, leveraging different feature representations and data augmentations along with the marginal benefits they bring on the table. Experimental results show that the proposed systems and preprocessing methods effectively learn acoustic characteristics from the audio recordings, and their ensemble model significantly reduces the error rate further, exhibiting a MAP@3 score of 0.945 and 0.947 respectively on the public leaderboard. The baseline score for this task has been 0.704 (public LB score)."
}

@techreport{Colangelo2018,
    Author = "Colangelo, Federico and Battisti, Federica and Neri, Alessandro and Carli, Marco",
    title = "CONVOLUTIONAL RECURRENT NEURAL NETWORK FOR AUDIO EVENTS CLASSIFICATION",
    institution = "DCASE2018 Challenge",
    year = "2018",
    month = "September",
    abstract = "Audio event recognition is becoming a hot topic both in the research and in the industrial field. Nowadays, thanks to the availability of cheap sensors, the acquisition of high-quality audio is much easier. However, new challenges arise: the large number of inputs requires adequate means for coding, transmitting, and storing the recorded data. Moreover, to build systems that can act based on their surroundings (e.g. autonomous cars), automatic tools for detecting specific audio events are needed. In this paper, the effectiveness of an architecture based on a combination of convolutional and re- current neural networks for general purpose audio event detection is evaluated. Specifically, the architecture is evaluated in the context of the DCASE challenge on general purpose audio tagging, in order to provide a clear comparison with architectures based on different principles."
}

@techreport{Dorfer2018,
    Author = "Dorfer, Matthias and Widmer, Gerhard",
    title = "GTRAINING GENERAL-PURPOSE AUDIO TAGGING NETWORKS WITH NOISY LABELS AND ITERATIVE SELF-VERIFICATION",
    institution = "DCASE2018 Challenge",
    year = "2018",
    month = "September",
    abstract = "This work describes our submission to the first Freesound general- purpose audio tagging challenge carried out within the DCASE 2018 challenge. Our solution is based on a fully convolutional neural network that predicts one out of 41 possible audio class labels when given an audio spectrogram excerpt as an input. What makes this classification dataset and the task in general special, is the fact that only 3,700 of the 9,500 provided training examples are delivered with manually verified ground truth labels. The remaining non- verified observations are expected to contain a substantial amount of label noise (30-35\%). We propose to address this issue by a simple, iterative self-verification process, which gradually shifts unverified labels into the verified, trusted training set. The decision criterion for self-verifying a training example is the prediction consensus of a previous snapshot of the network on multiple short sliding window excerpts of the training example at hand. This procedure requires a carefully chosen cross-validation setup, as large enough neural net- works are able to learn an entire dataset by heart, even in the face of noisy label data. On the unseen test data, an ensemble of three net- works trained with this self-verification approach achieves a mean average precision (MAP@3) of 0.951. This is the second best out of 558 submissions to the corresponding Kaggle challenge."
}

@techreport{Fonseca2018,
    Author = "Fonseca, Eduardo and Plakal, Manoj and Font, Frederic and Ellis, Daniel P. W. and Serra, Xavier",
    title = "GENERAL-PURPOSE TAGGING OF FREESOUND AUDIO WITH AUDIOSET LABELS: TASK DESCRIPTION, DATASET, AND BASELINE",
    institution = "DCASE2018 Challenge",
    year = "2018",
    month = "September",
    abstract = "This paper describes Task 2 of the DCASE 2018 Challenge, titled “General-purpose audio tagging of Freesound content with Au- dioSet labels”. This task was hosted on the Kaggle platform as “Freesound General-Purpose Audio Tagging Challenge”. The goal of the task is to build an audio tagging system that can recognize the category of an audio clip from a subset of 41 diverse categories drawn from the AudioSet Ontology. We present the task, the dataset prepared for the competition, and a baseline system."
}

@techreport{Han2018,
    Author = "Han, Xueyu and Li, Di and Liu, Qing",
    title = "CIAIC-GATFC SYSTEM FOR DCASE2018 CHALLENGE TASK2",
    institution = "DCASE2018 Challenge",
    year = "2018",
    month = "September",
    abstract = "In this report, we present our method to tackle the problem of general-purpose automatic audio tagging described in DCASE 2018 challenge task 2. Two convolutional neural networks (CNN) models with different inputs and different architectures were trained respectively. Outputs from the two CNN models were then fused together to give a final decision. In particular, the distribution of training samples among 41 categories were unequally. Therefore, we presented a data augmentation method, which guaranteed the number of training samples per category was equal. A relative 21.4\% improvement over DCASE baseline system [1] is achieved on the public Kaggle leaderboard."
}

@techreport{Hanyu2018,
    Author = "Hanyu, Zhang and Shengchen, Li",
    title = "A SYSTEM FOR DCASE CHALLENGE USING 2018 CRNN WITH MEL FEATURES",
    institution = "DCASE2018 Challenge",
    year = "2018",
    month = "September",
    abstract = "For the Acoustic Scene Classification task (General-purpose audio tagging of Freesound content with AudioSet labels) of the IEEE AASP Challenge on Detection and Classification of Acoustic Scenes and Events (DCASE 2018), we propose a method to classify 41 different acoustic events using a Convolutional Recurrent Neural Network (CRNN) with log Mel spectrogram. First, the waveform of the audio recordings is transformed to log Mel spectrogram and MFCC. The convolutional layers are then applied on the log Mel spectrogram and Mel-frequency cepstral coefficients to extract high level features. The features are fed into the Recurrent Neural Network (RNN) for classification. On the official development set of the challenge, the best MAP is 0.8613, which increases 6.83\% compared with the base- line."
}

@techreport{Iqbal2018,
    Author = "Iqbal, Turab and Kong, Qiuqiang and Plumbley, Mark and Wang, Wenwu",
    title = "STACKED CONVOLUTIONAL NEURAL NETWORKS FOR GENERAL-PURPOSE AUDIO TAGGING",
    institution = "DCASE2018 Challenge",
    year = "2018",
    month = "September",
    abstract = "This technical report describes the methods used for classifying sound events as part of Task 2 of the DCASE 2018 challenge. The data used in this task requires a number of considerations, including how to handle variable-length audio samples and the presence of noisy labels. We propose a number of neural network architectures that learn from mel-spectrogram inputs. These baseline models involve the use of preprocessing techniques, data augmentation, and pseudo-labeling in order to improve their performance. They are then ensembled using a popular technique known as stacking. On the test set used for evaluation, compared to the baseline mean average precision score of 0.704, our system achieved a score of 0.961."
}

@techreport{Jeong2018,
    Author = "Jeong, Il-Young and Lim, Hyungui",
    title = "AUDIO TAGGING SYSTEM FOR DCASE 2018: FOCUSING ON LABEL NOISE, DATA AUGMENTATION AND ITS EFFICIENT LEARNING",
    institution = "DCASE2018 Challenge",
    year = "2018",
    month = "September",
    abstract = "In this technical report, we expound on the techniques and models applied to our submission for DCASE 2018: General-purpose audio tagging of Freesound content with AudioSet labels. We aim to focus primarily on how to train a deep-learning model efficiently against strong augmentation and label noise. First, we conducted a single-block DenseNet architecture and multi-head softmax classifier for efficient learning with mixup augmentation. For the label noise, we tried the batch-wise loss masking, which eliminates the loss of outliers in a mini-batch. We also tried an ensemble of various models, trained by using different sampling rate or audio representation."
}

@techreport{Kele2018,
    Author = "Kele, Xu and Boqing, Zhu and Dezhi, Wang and Yuxing, Peng and Huaimin, Wang and Lilun, Zhang and Bo, Li",
    title = "NUDT SOLUTION FOR AUDIO TAGGING TASK OF DCASE 2018 CHALLENGE",
    institution = "DCASE2018 Challenge",
    year = "2018",
    month = "September",
    abstract = "In this technical report, we describe our solution for the general- purpose audio tagging task, which belongs to one of the subtasks in the DCASE 2018 challenge. For the solution, we employed both deep learning methods and statistic features-based shallow architecture learners. For single model, only deep learning approaches are investigated, and different deep neural network architectures are tested with different kinds of input, which ranges from the raw- signal, log-scaled Mel-spectrograms (log Mel) to Mel Frequency Cepstral Coefficents (MFCC). For log Mel and MFCC, the delta and delta-delta information are also used to formulate three-channels features. Inception, ResNet, ResNeXt, Dual Path Networks (DPN) are selected as the neural network architectures, while Mixup is used for the data augmentation. Using ResNeXt, our best single convolutional neural network architecture provides an mAP@3 of 0.967 on the public Kaggle leaderboard. Moreover, to improve the accuracy further, we also propose a meta learning-based ensemble method. By employing the diversities between different architectures, the meta learning- based model can provide higher prediction accuracy and robustness with comparison to the single model. Using the proposed meta- learning method, our solution achieves an mAP@3 of 0.977 (rank 1 of 555) on the public Kaggle leaderboard, while the baseline gives an mAP@3 of 0.70."
}

@techreport{Khadkevich2018,
    Author = "Khadkevich, Maksim",
    title = "ACOUSTIC SCENE AND EVENT DETECTION SYSTEMS SUBMITTED TO DCASE 2018 CHALLENGE",
    institution = "DCASE2018 Challenge",
    year = "2018",
    month = "September",
    abstract = "In this technical report we describe systems that have been submitted to DCASE 2018 challenge. Feature extraction and convolutional neural network (CNN) architecture are outlined. For tasks 1c and 2 we describe transfer learning approach that has been applied. Model training and inference are finally presented."
}

@techreport{Kim2018,
    Author = "Kim, Nam Kyun and Yang, Jeong Hyeon and Kim, Hong Kook and Lim, Jeong Eun and Park, Jin Soo and Park, Ji Hyun",
    title = "GIST\_WISENETAI AUDIO TAGGER BASED ON CONCATENATED RESIDUAL NETWORK FOR DCASE 2018 CHALLENGE TASK 2",
    institution = "DCASE2018 Challenge",
    year = "2018",
    month = "September",
    abstract = "In this report, we describe the method and performance of an acoustic event tagger applied to the Task 2 of the Detection and Classification of Acoustic Scene and Events 2018 (DCASE 2018) challenge, where the task evaluates systems for general-purpose audio tagging with an increased number of categories and using data with annotations of varying reliability. The proposed audio tagger, which is call GIST\_WisenetAI and developed by the collaboration of GIST and Hanwha Techwin, is based on a concatenated residual network (ConResNet). In particular, the proposed ConResNet is composed of two types of convolutional neural net- work (CNN) residual networks (CNN-ResNet) such as a 2D CNN-ResNet and an 1D CNN-ResNet using a sequence of mel- frequency cepstrum coefficients (MFCCs) and their statistics, respectively, as input features. In order to improve the performance of audio tagging, k different ConResNets are trained using k-fold cross-validation, and then they are linearly combined to generate an ensemble classifier. In this task, 9,473 audio samples for training/validation are divided into 10 folds, and 9,400 audio sample are given for testing. Consequently, the proposed method provides the mean average precision up to top 3 (MAP@3) of 0.958, which is measured through the Kaggle platform."
}

@techreport{Kong2018,
    Author = "Kong, Qiuqiang and Turab, Iqbal and Yong, Xu and Wang, Wenwu and Plumbley, Mark D.",
    title = "DCASE 2018 CHALLENGE SURREY CROSS-TASK CONVOLUTIONAL NEURAL NETWORK BASELINE",
    institution = "DCASE2018 Challenge",
    year = "2018",
    month = "September",
    abstract = "Detection and classification of acoustic scenes and events (DCASE) 2018 challenge is a well known IEEE AASP challenge consists of several audio classification and sound event detection tasks. DCASE 2018 challenge includes five tasks: 1) Acoustic scene classification, 2) Audio tagging of Freesound, 3) Bird audio detection, 4) Weakly labeled semi-supervised sound event detection and 5) Multi-channel audio tagging. In this paper we open source the python code of all of Task 1 - 5 of DCASE 2018 challenge. The baseline source code contains the implementation of the convolutioanl neural networks (CNNs) including the AlexNetish and the VGGish from the image processing area. We researched how the performance varies from task to task when the configuration of the neural networks are the same. The experiment shows deeper VGGish network performs better than AlexNetish on Task 2 - 5 except Task 1 where VGGish and AlexNetish network perform similar. With the VGGish network, we achieve an accuracy of 0.680 on Task 1, a mean average precision (mAP) of 0.928 on Task 2, an area under the curve (AUC) of 0.854 on Task 3, a sound event detection F1 score of 20.8\% on Task 4 and a F1 score of 87.75\% on Task 5."
}

@techreport{Nguyen2018,
    Author = "Nguyen, Thi Ngoc Tho and Nguyen, Ngoc Khanh and Jones, Douglas L. and Gan, Woon Seng",
    title = "DCASE 2018 TASK 2: ITERATIVE TRAINING, LABEL SMOOTHING, AND BACKGROUND NOISE NORMALIZATION FOR AUDIO EVENT TAGGING",
    institution = "DCASE2018 Challenge",
    year = "2018",
    month = "September",
    abstract = "This paper describes an approach from our submissions for DCASE 2018 Task 2: general-purpose audio tagging of Freesound content with AudioSet labels. To tackle the problem of diverse recording environments, we propose to use background noise normalization. To tackle the problem of noisy labels, we propose to use pseudo- label for automatic label verification and label smoothing to reduce the over-fitting. We train several convolutional neural networks with data augmentation and different input sizes for the automatic label verification process. The procedure is promising to improve the quality of datasets for audio classification. On the public leader board for the competition, our single model and an ensemble of 8 models score 0.941 and 0.963 respectively."
}

@techreport{Pantic2018,
    Author = "Pantic, Bogdan",
    title = "ENSEMBLE OF CONVOLUTIONAL NEURAL NETWORKS FOR GENERAL PURPOSE AUDIO TAGGING",
    institution = "DCASE2018 Challenge",
    year = "2018",
    month = "September",
    abstract = "This work describes our solution for the general purpose audio tagging task of the DCASE 2018 challenge. We propose ensemble of several Convolutional Neural Networks (CNNs) with different properties. Logistic regression is used as meta-classifier to produce final predictions. Experiments demonstrate that ensemble outperforms each CNN individually. Finally, proposed system achieves Mean Average Precision (MAP) score of 0.956 on public leaderboard, which is significant improvement compared to base- line."
}

@techreport{Ren2018,
    Author = "Shan, Siyuan and Ren, Yi",
    title = "AUTOMATIC AUDIO TAGGING WITH 1D AND 2D CONVOLUTIONAL NEURAL NETWORKS",
    institution = "DCASE2018 Challenge",
    year = "2018",
    month = "September",
    abstract = "In this work, we ensemble four different models for the audio tagging tasks. The first two models are 2D convolutional neural net- works (CNNs) that respectively take Mel spectrogram and MFCC spectrogram as input features, while other last two models are two 1D CNNs architectures that take raw waveform as inputs. Data augmentation techniques, including time stretch, pitch shift, reverb and dynamic range compression, are also employed for better generalization. Transfer learning from two external datasets is also adopted. These components together contribute to our final recognition performance reported on Kaggle."
}

@techreport{WEI2018,
    Author = "WEI, Qingkai and LIU, Yanfang and RUAN, Xiaohui",
    title = "A REPORT ON AUDIO TAGGING WITH DEEPER CNN, 1D-CONVNET AND 2D-CONVNET",
    institution = "DCASE2018 Challenge",
    year = "2018",
    month = "September",
    abstract = "General-purpose audio tagging is a newly proposed task in DCASE 2018, which can provide insight towards broadly-applicable sound event classifiers. In this paper, two systems (named as 1D-ConvNet and 2D-ConvNet in this paper) with small kernel sizes, multiple functional modules, deeper CNN (convolutional neural network- s) are developed to improve performance in this task. Different audio features are used: raw waveforms are for 1D-ConvNet; frequency domain features such as mfcc, log-mel spectrogram, multi-resolution log-mel spectrogram and spectrogram, are compared as the 2D-ConvNet input. Using DCASE 2018 Challenge task 2 dataset to train and evaluate, the best single model with 1D- ConvNet and 2D-ConvNet are chosen, whose kaggle public leader- board score are 0.877 and 0.961 respectively. In addition, a better ensemble rank averaging prediction get a score 0.968 on the public leaderboard, ranking 5/556."
}

@techreport{Wilhelm2018,
    Author = "Wilhelm, Benjamin and Lederle, Marcel",
    title = "COMBINING HIGH-LEVEL FEATURES OF RAW AUDIO AND SPECTROGRAMS FOR AUDIO TAGGING",
    institution = "DCASE2018 Challenge",
    year = "2018",
    month = "September",
    abstract = "We introduce a method for general-purpose audio tagging that combines high-level features computed from the spectrogram and raw audio data. We use convolutional neural networks with one- dimensional and two-dimensional convolutions to extract these useful high-level features and combine them with a densely connected neural network to make predictions. Our method performs in the top two percent of on the Freesound General-Purpose Audio Tagging Challenge."
}

@techreport{Wilkinghoff2018,
    Author = "Wilkinghoff, Kevin",
    title = "GENERAL-PURPOSE AUDIO TAGGING BY ENSEMBLING CONVOLUTIONAL NEURAL NETWORKS BASED ON MULTIPLE FEATURES",
    institution = "DCASE2018 Challenge",
    year = "2018",
    month = "September",
    abstract = "This paper describes an audio tagging system which participated in Task 2 “General-purpose audio tagging of Freesound content with AudioSet labels” of the “Detection and Classification of Acoustic Scenes and Events (DCASE)” Challenge 2018. The system is an ensemble consisting of five convolutional neural networks based on Mel-frequency Cepstral Coefficients, Perceptual Linear Prediction features, Mel-spectrograms and the raw audio data. For ensembling all models, score-based fusion via Logistic Regression is per- formed with another neural network. In experimental evaluations, it is shown that ensembling the models significantly improves upon the performances obtained with the individual models."
}

@techreport{Xu2018,
    Author = "Xu, Zhicun and Smit, Peter and Kurimo, Mikko",
    title = "THE AALTO SYSTEM BASED ON FINE-TUNED AUDIOSET FEATURES FOR DCASE2018 TASK2 —— GENERAL PURPOSE AUDIO TAGGING",
    institution = "DCASE2018 Challenge",
    year = "2018",
    month = "September",
    abstract = "In this paper, we presented a neural network system for DCASE 2018 task 2, general purpose audio tagging. We fine-tuned the Google AudioSet feature generation model with different settings for the given 41 classes on top of a fully connected layer with 100 units. Then we used the fine-tuned models to generate 128 dimensional features for each 0.960s audio. We tried different neural net- work structures including LSTM and multi-level attention models. In our experiments, the multi-level attention model has shown its superiority over others. Truncating the silence parts, repeating and splitting the audio into the fixed length, pitch shifting augmentation, and mixup techniques have all improved the results with a reason- able amount. The proposed system achieved a result with MAP@3 score at 0.936, which outperforms the baseline result of 0.704 and achieves top 7\% in the public leaderboard."
}

@techreport{Yu2018,
    Author = "Yu, Zhesong",
    title = "MODEL OF B-CNN AND WAVENET IN TASK 2",
    institution = "DCASE2018 Challenge",
    year = "2018",
    month = "September",
    abstract = "The system has two parts, one is BCNN in MFCC, another is WaveNet in raw audio. B-CNN is a model proposed to solve Im- age fine classification task, and WaveNet is a model used to music generation. And the propose of this paper is just to see the performance of the two model in music classification task."
}