Convolutional gated recurrent neural network incorporating spatial features for audio tagging

Abstract

Abstract-Environmental audio tagging is a newly proposed task to predict the presence or absence of a specific audio event in a chunk. Deep neural network (DNN) based methods have been successfully adopted for predicting the audio tags in the domestic audio scene. In this paper, we propose to use a convolutional neural network (CNN) to extract robust features from mel-filter banks (MFBs), spectrograms or even raw waveforms for audio tagging. Gated recurrent unit (GRU) based recurrent neural networks (RNNs) are then cascaded to model the long-term temporal structure of the audio signal. To complement the input information, an auxiliary CNN is designed to learn on the spatial features of stereo recordings. We evaluate our proposed methods on Task 4 (audio tagging) of the Detection and Classification of Acoustic Scenes and Events 2016 (DCASE 2016) challenge. Compared with our recent DNN-based method, the proposed structure can reduce the equal error rate (EER) from 0.13 to 0.11 on the development set. The spatial features can further reduce the EER to 0.10. The performance of the end-to-end learning on raw waveforms is also comparable. Finally, on the evaluation set, we get the state-of-the-art performance with 0.12 EER while the performance of the best existing system is 0.15 EER.

Semi-supervised Acoustic Event Detection Based on Tri-training

“…As we have to run inference on large amount of unlabeled data, inference speed is also an important factor along with the accuracy. Our experimented models include ResNet [24], DenseNet and Conv-RNN [25,26] with different lay-ers, which are among the state-of-the-art models for acoustic event detection. According to our experiments, DenseNet-63 achieves highest accuracy and also has relative small inference latency.…”

Mixup-Based Acoustic Scene Classification Using Multi-channel Convolutional Neural Network

“…Recently, due to the release of the relatively larger labeled data, there has been a plethora of efforts have been made for the audio scene classification task [7], [8]. In brief, the main contributions can be divided into three parts: the representation of the audio signal (or handcrafted feature design) [9], [10], [11]; more sophisticated shallow-architecture classifiers [12], [13], [14] and the applications of deep learning in ASC task [15], [16].…”

“…Indeed, deep learning has witnessed dramatic progress during the last decade and achieved success in several different fields, such as, image classification [16], speech recognition [17], natural language processing [18] and so on. Although, there are some attempts, which employ CNN as the tool to solve the ASC task, most of them tried to solve the problem within the context of using the monaural signals.…”

Deep Learning for Audio Event Detection and Tagging on Low-Resource Datasets

“…When using a large enough dataset that provides satisfactory training data and has a a good representation for each different class, many methods have been successful in performing both of the intermediate tasks. A few methods for audio event detection can be found in [9] and [22], while for audio tagging in [12,24,25,1,19,6]. These tasks are less challenging to train for than Figure 1: Factorisation of the full transcription task.…”

“…Furthermore, considering that only chunk level rather than frame-level labels are available, a large set of contextual frames of the chunk were fed into the network to perform this task. In [25,1], the authors use a stacked convolutionla recurrent network to perform environmental audio tagging and tag the presence of birdsong, respectively. While in [19], the authors explore two different models for end-to-end music audio tagging when there is a large amount of training data.…”