Detection of
rare sound events

@techreport{Cakir2017,
    Author = "Cakir, Emre and Virtanen, Tuomas",
    title = "Convolutional Recurrent Neural Networks for Rare Sound Event Detection",
    institution = "DCASE2017 Challenge",
    year = "2017",
    month = "September",
    abstract = "Sound events possess certain temporal and spectral structure in their time-frequency representations. The spectral content for the samples of the same sound event class may exhibit small shifts due to intra-class acoustic variability. Convolutional layers can be used to learn high-level, shift invariant features from time-frequency representations of acoustic samples, while recurrent layers can be used to learn the longer term temporal context from the extracted high-level features. In this paper, we propose combining these two in a convolutional recurrent neural network (CRNN) for rare sound event detection. The proposed method is evaluated over DCASE 2017 challenge dataset of individual sound event samples mixed with everyday acoustic scene samples. CRNN provides significant performance improvement over two other deep learning based methods mainly due to its capability of longer term temporal modeling."
}

@techreport{Dang2017,
    Author = "Dang, An and Vu, Toan and Wang, Jia-Ching",
    title = "Deep Learning for {DCASE2017} Challenge",
    institution = "DCASE2017 Challenge",
    year = "2017",
    month = "September",
    abstract = "This paper reports our results on all tasks of DCASE challenge 2017 which are acoustic scene classification, detection of rare sound events, sound event detection in real life audio, and large-scale weakly supervised sound event detection for smart cars. Our proposed methods are developed based on two favorite neural networks which are convolutional neural networks (CNNs) and recurrent neural networks (RNNs). Experiments show that our proposed methods outperform the baseline."
}

@techreport{Ghaffarzadegan2017,
    Author = "Ghaffarzadegan, Shabnam and Salekin, Asif and Das, Samarjit and Feng, Zhe",
    title = "Bosch Rare Sound Events Detection Systems for {DCASE2017} Challenge",
    institution = "DCASE2017 Challenge",
    year = "2017",
    month = "September",
    abstract = "In this report, we describe three systems designed at BOSCH for rare audio sound events detection task of DCASE 2017 challenge. The first system is an end-to-end audio event segmentation using embeddings based on deep convolutional neural network (DCNN) and deep recurrent neural network (DRNN) trained on Mel-filter banks and spectogram features. Both system 2 and 3 contain two parts: audio event tagging and audio event segmentation. Audio event tagging selects the positive audio recordings (containing audio events), which are later processed by the audio segmentation part. Feature selection method has been deployed to select a subset of features in both systems. System 2 employs Dilated convolutional neural network on the selected features for audio tagging, and an audio-codebook approach to convert audio features to audio vectors (Audio2vec system) which are then passed to an LSTM network for audio events boundary prediction. System 3 is based on multiple instance learning problem using variational auto encoder (VAE) to perform audio event tagging and segmentation. Similar to system 2, here a LSTM network is used for audio segmentation. Finally, we have utilized models based on score-fusion among different systems to improve the final results."
}

@techreport{Heittola2017,
    Author = "Heittola, Toni and Mesaros, Annamaria",
    title = "{DCASE} 2017 Challenge Setup: Tasks, Datasets and Baseline System",
    institution = "DCASE2017 Challenge",
    year = "2017",
    month = "September",
    abstract = "DCASE 2017 Challenge consists of four tasks: acoustic scene classification, detection of rare sound events, sound event detection in real-life audio, and large-scale weakly supervised sound event detection for smart cars. This paper presents the setup of these tasks: task definition, dataset, experimental setup, and baseline system results on the development dataset. The baseline systems for all tasks rely on the same implementation using multilayer perceptron and log mel-energies, but differ in the structure of the output layer and the decision making process, as well as the evaluation of system output using task specific metrics."
}

@techreport{Jeon2017,
    Author = "Jeon, Kwang Myung and Kim, Hong Kook",
    title = "Nonnegative Matrix Factorization-Based Source Separation with Online Noise Learning for Detection of Rare Sound Events",
    institution = "DCASE2017 Challenge",
    year = "2017",
    month = "September",
    abstract = "In this paper, a source separation method based on nonnegative matrix factorization (NMF) with online noise learning (ONL) is proposed for the robust detection of rare sound events. The pro-posed method models the rare sound event into combinations of acoustic dictionaries, which consist of multiple spectral bases. In addition, ONL is adopted during the separation to improve the robustness against unseen noises. The spectra of the sound event separated by the proposed method act as a feature vector for the deep neural network (DNN)-based binary classifier, which deter-mines whether the event has occurred. The evaluation results using the DCASE 2017 Task 2 Dataset show that the proposed source separation method improved the F-score of the baseline DNN classifier by 6.30\% while decreasing the error rate by 14.81\% on average."
}

@techreport{Kaiwu2017,
    Author = "Kaiwu, Wang and Liping, Yang and Bin, Yang",
    title = "Audio Events Detection and Classification Using Extended {R-FCN} Approach",
    institution = "DCASE2017 Challenge",
    year = "2017",
    month = "September",
    abstract = "In this study, we present a new audio events detection and classification approach based on R-FCN—a state-of-the-art fully convolutional network framework for visual object detection. Spectrogram features of audio signals are used as the input of the approach. The proposed approach consists of two parts like R-FCN network. In the first part, we detect whether there are audio events by the sliding of convolutional kernel in time axis and proposals which possibly contain audio events are generated by RPN (Region Proposal Networks). In the second part, time and frequency information are integrated to classify these proposals and refine their boundaries by R-FCN. Our approach can process arbitrary length audio signals without any post-processing. Experiments on the dataset of IEEE DCASE Challenge 2017 Task 2 show that the proposed approach achieved great performance, an average F score of 91.4 \%, Error Rate of 0.16 on the event-based evaluation metrics."
}

@techreport{Li2017,
    Author = "Li, Yanxiong and Li, Xianku",
    title = "The {SEIE-SCUT} Systems for {IEEE} {AASP} Challenge on {DCASE} 2017: Deep Learning Techniques for Audio Representation and Classification",
    institution = "DCASE2017 Challenge",
    year = "2017",
    month = "September",
    abstract = "In this report, we present our works about three tasks of IEEE AASP challenge on DCASE 2017, i.e. task 1: Acoustic Scene Classification (ASC), task 2: detection of rare sound events in artificially created mixtures and task 3: sound event detection in real life recordings. Tasks 2 and 3 belong to the same problem, i.e. Sound Event Detection (SED). We adopt deep learning techniques to extract Deep Audio Feature (DAF) and classify various acoustic scenes or sound events. Specifically, a Deep Neural Network (DNN) is first built for generating the DAF from Mel-Frequency Cepstral Coefficients (MFCCs), and then a Recurrent Neural Network (RNN) of Bi-directional Long Short Term Memory (Bi-LSTM) fed by the DAF is built for ASC and SED. Evaluated on the development datasets of DCASE 2017, our systems are superior to the corresponding baselines for tasks 1 and 2, and our system for task 3 performs as good as the baseline in terms of the predominant metrics."
}

@techreport{Lim2017,
    Author = "Lim, Hyungui and Park, Jeongsoo and Han, Yoonchang",
    title = "Rare Sound Event Detection Using {1D} Convolutional Recurrent Neural Networks",
    institution = "DCASE2017 Challenge",
    year = "2017",
    month = "September",
    abstract = "Rare sound event detection is a newly proposed task in IEEE DCASE 2017 to identify the presence of monophonic sound event that is classified as an emergency and to detect the onset time of the event. In this paper, we introduce a rare sound event detection system using combination of 1D convolutional neural network (1D ConvNet) and recurrent neural network (RNN) with long short-term memory units (LSTM). A log-amplitude mel-spectrogram is used as an input acoustic feature and the 1D ConvNet is applied in each time domain segment to convert the spectral feature. Then the RNN-LSTM is utilized to incorporate the temporal dependency of the extracted features. The system is evaluated using DCASE 2017 Challenge Task 2 Dataset. Our best result on the test set of the development dataset shows 0.07 and 96.26 of error rate and F-Score on event-based metric, respectively."
}

@techreport{Phan2017,
    Author = "Phan, Huy and Krawczyk-Becker, Martin and Gerkmann, Timo and Mertins, Alfred",
    title = "{DNN} and {CNN} with Weighted and Multi-Task Loss Functions for Audio Event Detection",
    institution = "DCASE2017 Challenge",
    year = "2017",
    month = "September",
    abstract = {This report presents our audio event detection system submitted for Task 2, "Detection of rare sound events", of DCASE 2017 challenge. The proposed system is based on convolutional neural networks (CNNs) and deep neural networks (DNNs) coupled with novel weighted and multi-task loss functions and state-of-the-art phase-aware signal enhancement. The loss functions are tailored for audio event detection in audio streams. The weighted loss is designed to tackle the common issue of imbalanced data in background/foreground classification while the multi-task loss enables the networks to simultaneously model the class distribution and the temporal structures of the target events for recognition. Our proposed systems significantly outperform the challenge baseline, improving F-score from 72.7\% to 89.8\% and reducing detection error rate from 0.53 to 0.19 on average.}
}

@techreport{Ravichandran2017,
    Author = "Ravichandran, Anravich and Das, Samarjit",
    title = "Bosch Rare Sound Events Detection Systems for {DCASE2017} Challenge",
    institution = "DCASE2017 Challenge",
    year = "2017",
    month = "September",
    abstract = "In this report, we describe three systems designed at BOSCH for rare audio sound events detection task of DCASE 2017 challenge. The first system is an end-to-end audio event segmentation using embeddings based on deep convolutional neural network (DCNN) and deep recurrent neural network (DRNN) trained on Mel-filter banks and spectogram features. Both system 2 and 3 contain two parts: audio event tagging and audio event segmentation. Audio event tagging selects the positive audio recordings (containing audio events), which are later processed by the audio segmentation part. Feature selection method has been deployed to select a subset of features in both systems. System 2 employs Dilated convolutional neural network on the selected features for audio tagging, and an audio-codebook approach to convert audio features to audio vectors (Audio2vec system) which are then passed to an LSTM network for audio events boundary prediction. System 3 is based on multiple instance learning problem using variational auto encoder (VAE) to perform audio event tagging and segmentation. Similar to system 2, here a LSTM network is used for audio segmentation. Finally, we have utilized models based on score-fusion among different systems to improve the final results."
}

@techreport{Vesperini2017,
    Author = "Vesperini, Fabio and Droghini, Diego and Ferretti, Daniele and Principi, Emanuele and Gabrielli, Leonardo and Squartini, Stefano and Piazza, Francesco",
    title = "A Hierarchic Multi-Scaled Approach for Rare Sound Event Detection",
    institution = "DCASE2017 Challenge",
    year = "2017",
    month = "September",
    abstract = "We propose a system for rare sound event detection using hierarchical and multi-scaled approach based on Multi Layer Perceptron (MLP) and Convolutional Neural Networks (CNN). It is our contribution to the rare sound event detection task of the IEEE AASP Challenge on Detection and Classification of Acoustic Scenes and Events (DCASE2017). The task consists on detection of event onset from artificially generated mixtures. Acoustic features are extracted from the acoustic signals, successively first event detection stage is performed by an MLP based neural network which proposes contiguous blocks of frames to the second stage. The CNN refines the event detection of the prior network, intrinsically operating on a multi-scaled resolution and discarding blocks that contain background wrongly classified by the MLP as event. Finally the effective onset time of the active event is obtained. The achieved overall error rate and F-measure on the development testset are respectively equal to 0.18 and 90.9\%."
}

@techreport{Wang2017,
    Author = "Wang, Jun and Li, Shengchen",
    title = "Multi-Frame Concatenation for Detection of Rare Sound Events Based on Deep Neural Network",
    institution = "DCASE2017 Challenge",
    year = "2017",
    month = "September",
    abstract = "This paper proposes a Sound Event Detection (SED) system based on Deep Neural Network (DNN). Three DNN-based classifiers are trained for detecting three target sound events including baby cry, glass break and gun shot from the audio streams provided. This paper investigates the influence of different frame concatenation when detecting sound events. Our results illustrate that the number of frames concatenated affects the accuracy of SED. The SED system proposed is tested by Development Datasets provided by Detection of Rare Sound Events in DCASE Challenge 2017. The average accuracy of the detection is that F-score and Error Rate (ER) on event-based metrics are 84.98\% and 0.28, respectively."
}

@techreport{Wang2017a,
    Author = "Wang, Jianfei and Zhang, Weiqiang and Liu, Jia",
    title = "Transfer Learning Based {DNN}-{HMM} Hybrid System for Rare Sound Event Detection",
    institution = "DCASE2017 Challenge",
    year = "2017",
    month = "September",
    abstract = "In this paper, we propose an improved Deep Neural Network-Hidden Markov Model (DNN-HMM) hybrid system for rare sound event detection. The proposed system leverages transfer learning technology in the neural network training stage. Experiment results indicate that transfer learning is more efficient when the training samples are insufficient. We use the Multi-Layer Perception (MLP) system and standard DNN-HMM system as the baseline. The performance was evaluated on the DCASE2017 task 2 development dataset show that our proposed system outperforms the MLP and DNN-HMM baselines, and finally achieves an average error rate (ER) of 0.38 and 78.3\% F1-score on the event-based evaluation. The average error rate of proposed system is 15\% and 8\% absolutely lower than the MLP and DNN-HMM systems, respectively."
}

@techreport{Zhou2017,
    Author = "Zhou, Qing and Feng, Zuren",
    title = "Robust Sound Event Detection Through Noise Estimation and Source Separation Using {NMF}",
    institution = "DCASE2017 Challenge",
    year = "2017",
    month = "September",
    abstract = "This paper addresses the problem of sound event detection under non-stationary noises and various real-world acoustic scenes. An effective noise reduction strategy is proposed in this paper which can automatically adapt to background variations. The proposed method is based on supervised non-negative matrix factorization (NMF) for separating target events from noise. The event dictionary is trained offline using the training data of the target event class while the noise dictionary is learned online from the input signal by sparse and low-rank decomposition. Incorporating the estimated noise bases, this method can produce accurate source separation results by reducing noise residue and signal distortion of the reconstructed event spectrogram. Experimental results on DCASE 2017 task 2 dataset show that the proposed method outperforms the baseline system based on multi-layer perceptron classifiers and also another NMF-based method which employs a semi-supervised strategy for noise reduction."
}