Sound event detection
in real life audio

@techreport{Adavanne2017,
    Author = "Adavanne, Sharath and Virtanen, Tuomas",
    title = "A Report on Sound Event Detection with Different Binaural Features",
    institution = "DCASE2017 Challenge",
    year = "2017",
    month = "September",
    abstract = "In this paper, we compare the performance of using binaural audio features in place of single channel features for sound event detection. Three different binaural features are studied and evaluated on the publicly available TUT Sound Events 2017 dataset of length 70 minutes. Sound event detection is performed separately with single channel and binaural features using stacked convolutional and recurrent neural network and the evaluation is reported using standard metrics of error rate and F-score. The studied binaural features are seen to consistently perform equal to or better than the single-channel features with respect to error rate metric."
}

@techreport{Chen2017,
    Author = "Chen, Yukun and Zhang, Yichi and Duan, Zhiyao",
    title = "{DCASE2017} Sound Event Detection Using Convolutional Neural Network",
    institution = "DCASE2017 Challenge",
    year = "2017",
    month = "September",
    abstract = "The DCASE2017 Challenge Task 3 is to develop a sound event detection system of real life audio. In our setup, we merge the two channels into one, then use Mel-band energy to calculate the converted spectrum, and train the model based on convolu- tional neural network (CNN). The method we use achieves a 0.81 error rate on average for the four cross-validation folders. It proves the practicability of using CNN for sound event detection."
}

@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{Feroze2017,
    Author = "Feroze, Khizer and Maud, Abdur-Rehaman",
    title = "Comparison of Baseline System with Perceptual Linear Predictive Feature Using Neural Network for Sound Event Detection in Real Life Audio",
    institution = "DCASE2017 Challenge",
    year = "2017",
    month = "September",
    abstract = "For sound event detection of polyphonic sounds, we compare the performance of perceptual linear predictive (PLP) feature with Mel frequency cepstral coefficients (MFCC) using neural network classifier. The results are further compared with the performance of the baseline system given by DCASE 2017 (task 3). Our results show that using PLP based classifier, individual error rate (ER) for each event is improved compared to the baseline system. For car event, ER is improved by 10\%, for large vehicle event 23\%, for people walking event 26\% and some improvements are also ob-served in other events."
}

@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{Hou2017,
    Author = "Hou, Yuanbo and Li, Shengchen",
    title = "Sound Event Detection in Real Life Audio Using Multi-Model System",
    institution = "DCASE2017 Challenge",
    year = "2017",
    month = "September",
    abstract = "In this paper, we present a polyphonic sound event detection (SED) system based on a multi-model system. In the proposed multi-model system, we use one model based on Deep Neural Networks (DNN) to detect sound events of car, and five models based on Bi-directional Gated Recurrent Units Recurrent Neural Networks (BGRU-RNN) to detect other sound events including: brakes squeaking, children, large vehicle, people speaking and people walking. Since different classes sound events have differ-ent audio characteristics, we use different models to detect each class. The proposed multi-model system is trained and tested based on IEEE DCASE2017 Challenge: Sound Event Detection in Real Life Audio (Task 3) Development Dataset, the result yields up to 58.92\% and 0.60 in terms of F-Score and error rate on segment-based metric respectively."
}

@techreport{Jeong2017,
    Author = "Jeong, Il-Young and Lee, Subin and Han, Yoonchang and Lee, Kyogu",
    title = "Audio Event Detection Using Multiple-Input Convolutional Neural Network",
    institution = "DCASE2017 Challenge",
    year = "2017",
    month = "September",
    abstract = "This paper describes the model and training framework from our submission for DCASE 2017 task 3: sound event detection in real life audio. Our model basically follows convolutional neural network architecture, yet uses two input data of the short- and long-term audio signal. In the training stage, we calculated validation errors more frequently than one epoch with adaptive thresholds. We also used class-wise early stopping to find the best model for each class. The proposed model shows a meaningful improvements in cross validation experiments compared to the baseline system using the simple neural network."
}

@techreport{Kroos2017,
    Author = "Kroos, Christian and Plumbley, Mark D.",
    title = "Neuroevolution for Sound Event Detection in Real Life Audio: A Pilot Study",
    institution = "DCASE2017 Challenge",
    year = "2017",
    month = "September",
    abstract = "Neuroevolution techniques combine genetic algorithms with artificial neural networks, some of them evolving network topology along with the network weights. One of these latter techniques is the NeuroEvolution of Augmenting Topologies (NEAT) algorithm. For this pilot study we devised an extended variant (joint NEAT, J-NEAT), introducing co-evolution, and applied it to sound event detection in real life audio (task 3) in the DCASE 2017 challenge. Our research question was whether small networks could be evolved that would be able to compete with the much larger networks now typical for classification and detection tasks. We used the wavelet-based deep scattering transform and k-means clustering across the resulting scales (not across samples) to provide J-NEAT with a compact representation of the acoustic input. Results show that J-NEAT is capable of evolving small networks that match the performance of the baseline system in terms of the segment-based error metrics, while exhibiting a substantially better event-related error rate. The evolved networks were, however, narrowly outperformed by a comparable, experimenter-designed minimal single-layer feed-forward network. We discuss the question of evolving versus learning for supervised tasks."
}

@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{Lu2017,
    Author = "Lu, Rui and Duan, Zhiyao",
    title = "Bidirectional {GRU} for Sound Event Detection",
    institution = "DCASE2017 Challenge",
    year = "2017",
    month = "September",
    abstract = "Sound event detection (SED) aims to detect temporal boundaries of sound events given audio streams. Sound recordings in real life situations typically have many overlapping events, making this detection task much more difficult than classification and non- overlapping detection. Recently, multi-label recurrent neural net- works (RNNs) have become the main stream solutions for this poly- phonic sound event detection problem. However, similar to many other deep learning approaches, the relative scarcity of carefully labeled data has limited the capacity of RNNs. In this paper, we first present a multi label bi-directional recurrent neural network to model the temporal evolution of sound events. Then we propose the use of data augmentation to overcome the problem of data scarcity and explore the appropriate augmentation strategies that achieve better performance. We evaluate our approach on the development subset of the DCASE2017 task3 dataset. Combined with data augmentation and ensemble technique, we reduce the error rate by over 11\% compared to the officially published baseline system."
}

@techreport{Wang2017,
    Author = "Wang, Chun-Hao and You, Jun-Kai and Liu, Yi-Wen",
    title = "Sound Event Detection From Real-Life Audio by Training a Long Short-Term Memory Network with Mono and Stereo Features",
    institution = "DCASE2017 Challenge",
    year = "2017",
    month = "September",
    abstract = "In this paper, we trained and evaluated an acoustic sound event classifier that uses a combination of stereo and mono features. For stereo features, we treated the time difference of arrival (TDOA) as a random variable and calculated its probability density function. For mono features, Mel-frequency cepstral coefficients (MFCCs) and their 1st and 2nd derivatives were extracted. A recurrent neural network (RNN) with long-short term memory (LSTM) was constructed to perform multi-label classification. Training with the 4-fold validation dataset given by DCASE2017 challenge [5], model parameters were chosen based on the best average performance. The proposed TDOA plus MFCC features combined with the RNN-LSTM model achieved a segment-based error rate of 0.77."
}

@techreport{Xia2017,
    Author = "Xia, Xianjun and Togneri, Roberto and Sohel, Ferdous and Huang, David",
    title = "Class Wise Distance Based Acoustic Event Detection",
    institution = "DCASE2017 Challenge",
    year = "2017",
    month = "September",
    abstract = "In this paper, we propose a class wise distance based approach in a neural network based acoustic event detection system. The neural network output probabilities are updated by calculating the distance between the acoustic features of each frame and the class wise distance of each event class. The detected acoustic segments are re-evaluated segmentally using the class wise distances. Cross-validation detection results on the development set of DCASE2017 show the efficiency of the proposed method by achieving a 4\% absolute reduction in segment-based error rate compared to the baseline system."
}

@techreport{Yu2017,
    Author = "Yu, Chun-Yan and Liu, Huang and Qi, Zi-Ming",
    title = "Sound Event Detection Using Deep Random Forest",
    institution = "DCASE2017 Challenge",
    year = "2017",
    month = "September",
    abstract = "In this paper, we present our work on Task 3 Sound Event Detection in Real Life Audio [1]. The systems aim at dealing with the detection of overlapping audio events, where the detectors are based on deep random forest, a decision tree ensemble approach. For random forest has natural defect of detecting and classifying polyphonic events, the systems use one-vs-the-rest (OvR) mul-ticlass/multilabel strategy, fitting one deep random forest per event class. On the development data set, the system obtained error rate value of 0.82 and F-score of 38.2\%."
}

@techreport{Zhou2017,
    Author = "Zhou, Jianchao",
    title = "Sound Event Detection in Multichannel Audio {LSTM} Network",
    institution = "DCASE2017 Challenge",
    year = "2017",
    month = "September",
    abstract = "In this paper, a polyphonic sound event detection system is proposed. This system uses log mel-band energy features with long short term memory (LSTM) recurrent neural network. Human listeners have been successfully recognizing overlapping sound events by two ears. Motivated by that we propose to extend the system to use multichannel audio data. The original stereo (multichannel) audio signal has two channels, we construct three different channel data and use different fusion strategies to extend our system. Experiments show that our system achieved superior performances compared with the baselines."
}