Unsupervised Feature Learning Based on Deep Models for Environmental Audio Tagging

Abstract

Environmental audio tagging aims to predict only the presence or absence of certain acoustic events in the interested acoustic scene. In this paper we make contributions to audio tagging in two parts, respectively, acoustic modeling and feature learning. We propose to use a shrinking deep neural network (DNN) framework incorporating unsupervised feature learning to handle the multi-label classification task. For the acoustic modeling, a large set of contextual frames of the chunk are fed into the DNN to perform a multi-label classification for the expected tags, considering that only chunk (or utterance) level rather than frame-level labels are available. Dropout and background noise aware training are also adopted to improve the generalization capability of the DNNs. For the unsupervised feature learning, we propose to use a symmetric or asymmetric deep de-noising auto-encoder (syDAE or asyDAE) to generate new data-driven features from the logarithmic Mel-Filter Banks (MFBs) features. The new features, which are smoothed against background noise and more compact with contextual information, can further improve the performance of the DNN baseline. Compared with the standard Gaussian Mixture Model (GMM) baseline of the DCASE 2016 audio tagging challenge, our proposed method obtains a significant equal error rate (EER) reduction from 0.21 to 0.13 on the development set. The proposed asyDAE system can get a relative 6.7% EER reduction compared with the strong DNN baseline on the development set. Finally, the results also show that our approach obtains the state-of-the-art performance with 0.15 EER on the evaluation set of the DCASE 2016 audio tagging task while EER of the first prize of this challenge is 0.17

Spoken Language Identification Using ConvNets

“…Several state-of-the-art results on various audio classification tasks have been obtained by using log-Mel spectrograms of raw audio, as features [25]. Convolutional Neural Networks have demonstrated an excellent performance gain in classification of these features [26,10] against other machine learning techniques. It has been shown that using attention layers with ConvNets further enhanced their performance [13].…”

Enhancing Sound Texture in CNN-based Acoustic Scene Classification

“…The performance of speech and image recognition systems has been significantly improved with the use of deep neural networks and exploding amount of training data. Audio-related tasks, e.g., Acoustic Scene Classification (ASC) [1,2,3], Sound Event Detection (SED) [4,5,6] and Audio Tagging [7,8,9,10], have also received increasing attention in recent years. They have many real-world applications.…”

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.…”

“…In [6], the authors proposed a content-based automatic music tagging algorithm using deep convolutional neural networks. In [24], the authors proposed to use a shrinking deep neural network incorporating unsupervised feature learning to handle the multi-label audio tagging. 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.…”