Reinforcement Learning Based Speech Enhancement for Robust Speech Recognition

Yih Liang Shen, Chao Yuan Huang, Syu Siang Wang, Yu Tsao, Hsin Min Wang, Tai-Shih Chi

研究成果: Conference contribution同行評審

2 引文 斯高帕斯(Scopus)

摘要

Conventional deep neural network (DNN)-based speech enhancement (SE) approaches aim to minimize the mean square error (MSE) between enhanced speech and clean reference. The MSE-optimized model may not directly improve the performance of an automatic speech recognition (ASR) system. If the target is to minimize the recognition error, the recognition results should be used to design the objective function for optimizing the SE model. However, the structure of an ASR system, which consists of multiple units, such as acoustic and language models, is usually complex and not differentiable. In this study, we propose to adopt the reinforcement learning (RL) algorithm to optimize the SE model based on the recognition results. We evaluated the proposed RL-based SE system on the Mandarin Chinese broadcast news corpus (MATBN). Experimental results demonstrate that the proposed SE system can effectively improve the ASR results with a notable 12:40% and 19:23% error rate reductions for signal to noise ratio (SNR) at 0 dB and 5 dB conditions, respectively.

原文English
主出版物標題2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings
發行者Institute of Electrical and Electronics Engineers Inc.
頁面6750-6754
頁數5
ISBN(電子)9781479981311
DOIs
出版狀態Published - 1 五月 2019
事件44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Brighton, United Kingdom
持續時間: 12 五月 201917 五月 2019

出版系列

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

Conference

Conference44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019
國家United Kingdom
城市Brighton
期間12/05/1917/05/19

指紋 深入研究「Reinforcement Learning Based Speech Enhancement for Robust Speech Recognition」主題。共同形成了獨特的指紋。

引用此