An Attention-based Neural Network Approach for Single Channel Speech Enhancement

Xiang Hao, Changhao Shan, Yong Xu, Sining Sun, Lei Xie

科研成果: 书/报告/会议事项章节会议稿件同行评审

48 引用 (Scopus)

摘要

This paper proposes an attention-based neural network approach for single channel speech enhancement. Our work is inspired by the recent success of attention models in sequence-to-sequence learning. It is intuitive to use attention mechanism in speech enhancement as humans are able to focus on the important speech components in an audio stream with high attention while perceiving the unimportant region (e.g., noise or interference) in low attention, and thus adjust the focal point over time. Specifically, taking noisy spectrum as input, our model is composed of an LSTM based encoder, an attention mechanism and a speech generator, resulting in enhanced spectrum. Experiments show that, as compared with OM-LSA and the LSTM baseline, the proposed attention approach can consistently achieve better performance in terms of speech quality (PESQ) and intelligibility (STOI). More promisingly, the attention-based approach has better generalization ability to unseen noise conditions.

源语言英语
主期刊名2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings
出版商Institute of Electrical and Electronics Engineers Inc.
6895-6899
页数5
ISBN(电子版)9781479981311
DOI
出版状态已出版 - 5月 2019
活动44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Brighton, 英国
期限: 12 5月 201917 5月 2019

出版系列

姓名ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
2019-May
ISSN(印刷版)1520-6149

会议

会议44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019
国家/地区英国
Brighton
时期12/05/1917/05/19

指纹

探究 'An Attention-based Neural Network Approach for Single Channel Speech Enhancement' 的科研主题。它们共同构成独一无二的指纹。

引用此