Title: REINFORCEMENT LEARNING BASED SPEECH ENHANCEMENT FOR ROBUST SPEECH RECOGNITION
Authors: Shen, Yih-Liang
Huang, Chao-Yuan
Wang, Syu-Siang
Tsao, Yu
Wang, Hsin-Min
Chi, Tai-Shih
電機工程學系
Department of Electrical and Computer Engineering
Keywords: reinforcement learning;automatic speech recognition;speech enhancement;deep neural network;character error rate
Issue Date: 1-Jan-2019
Abstract: 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.
URI: http://hdl.handle.net/11536/152934
ISBN: 978-1-4799-8131-1
ISSN: 1520-6149
Journal: 2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP)
Begin Page: 6750
End Page: 6754
Appears in Collections:Conferences Paper