REINFORCEMENT LEARNING BASED SPEECH ENHANCEMENT FOR ROBUST SPEECH RECOGNITION
檔案
本條目沒有附加檔案。
日期
2019-01-01
類型
系所
期刊名稱
2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP)
卷期與頁次
頁 6750–6754
ISSN
1520-6149
ISBN
978-1-4799-8131-1
語言
英文
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.
關鍵詞
reinforcement learningautomatic speech recognitionspeech enhancementdeep neural networkcharacter error rate所屬典藏
會議論文引用此條目
Shen, Y.-L., Huang, C.-Y., Wang, S.-S., Tsao, Y., Wang, H.-M., & Chi, T.-S. (2019). REINFORCEMENT LEARNING BASED SPEECH ENHANCEMENT FOR ROBUST SPEECH RECOGNITION. 2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 6750–6754. https://ir.lib.nycu.edu.tw/handle/11536/152934
引用文字依 APA 第 7 版格式自動產生,使用前請再核對。
分享
永久網址:https://ir.lib.nycu.edu.tw/handle/11536/152934