Improving Audio Anomalies Recognition Using Temporal Convolutional Attention Networks
Authors:
- 6 June 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 6473-6477
Abstract
Anomalous audio in speech recordings is often caused by speaker voice distortion, external noise, or even electric interferences. These obstacles have become a serious problem in some fields, such as high-quality dubbing and speech processing. In this paper, a novel approach using a temporal convolutional attention network (TCAN) is proposed to tackle this problem. The use of temporal conventional network (TCN) can capture long range patterns using a hierarchy of temporal convolutional filters. To enhance the ability to tackle audio anomalies in different acoustic conditions, an attention mechanism is used in TCN, where a self-attention block is added after each temporal convolutional layer. This aims to high-light the target related features and mitigate the interferences from irrelevant information. To evaluate the performance of the proposed model, audio recordings are collected from the TIMIT dataset, and are then changed by adding five different types of audio distortions: gaussian noise, magnitude drift, random dropout, reduction of temporal resolution, and time warping. Distortions are mixed at different signal-to-noise ratios (SNRs) (5dB, 10dB, 15dB, 20dB, 25dB, 30dB). The experimental results show that the use of proposed model can yield better classification performances than some strong baseline methods, such as the LSTM and TCN based models, by approximate 3~ 10% relative improvements.Keywords
All Related Versions
Funding Information
- Innovate UK
This publication has 11 references indexed in Scilit:
- TCN-ATT: A Non-recurrent Model for Sequence-Based Malware Detection2020
- Efficient Convolutional Neural Networks for Diacritic Restoration2019
- Time-Frequency Mask-based Speech Enhancement using Convolutional Generative Adversarial Network2018
- Quality-Net: An End-to-End Non-intrusive Speech Quality Assessment Model Based on BLSTM2018
- Predicting speech intelligibility with deep neural networksComputer Speech & Language, 2018
- Temporal Convolutional Networks for Action Segmentation and Detection2017
- Novel deep autoencoder features for non-intrusive speech quality assessment2016
- A Decomposable Attention Model for Natural Language Inference2016
- Long Short-Term Memory-Networks for Machine Reading2016
- Mean opinion score (MOS) revisited: methods and applications, limitations and alternativesMultimedia Systems, 2014