Generalized weighted-prediction-error dereverberation with varying source priors for reverberant speech recognition

Toru Taniguchi, Aswin Shanmugam Subramanian, Xiaofei Wang, Dung Tran, Yuya Fujita, Shinji Watanabe

研究成果: Conference contribution

2 被引用数 (Scopus)

抄録

Weighted-prediction-error (WPE) is one of the well-known dereverberation signal processing methods especially for alleviating degradation of performance of automatic speech recognition (ASR) in a distant speaker scenario. WPE usually assumes that desired source signals always follow predefined specific source priors such as Gaussian with time-varying variances (TVG). Although based on this assumption WPE works well in practice, generally proper priors depend on sources, and they cannot be known in advance of the processing. On-demand estimation of source priors e.g. according to each utterance is thus required. For this purpose, we extend WPE by introducing a complex-valued generalized Gaussian (CGG) prior and its shape parameter estimator inside of processing to deal with a variety of super-Gaussian sources depending on sources. Blind estimation of the shape parameter of priors is realized by adding a shape parameter estimator as a sub-network to WPE-CGG, treated as a differentiable neural network. The sub-network can be trained by backpropagation from the outputs of the whole network using any criteria such as signal-level mean square error or even ASR errors if the WPE-CGG computational graph is connected to that of the ASR network. Experimental results show that the proposed method outperforms conventional baseline methods with the TVG prior without careful setting of the shape parameter value during evaluation.

本文言語English
ホスト出版物のタイトル2019 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, WASPAA 2019
出版社Institute of Electrical and Electronics Engineers Inc.
ページ293-297
ページ数5
ISBN(電子版)9781728111230
DOI
出版ステータスPublished - 2019 10
外部発表はい
イベント2019 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, WASPAA 2019 - New Paltz, United States
継続期間: 2019 10 202019 10 23

出版物シリーズ

名前IEEE Workshop on Applications of Signal Processing to Audio and Acoustics
2019-October
ISSN(印刷版)1931-1168
ISSN(電子版)1947-1629

Conference

Conference2019 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, WASPAA 2019
CountryUnited States
CityNew Paltz
Period19/10/2019/10/23

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Science Applications

フィンガープリント 「Generalized weighted-prediction-error dereverberation with varying source priors for reverberant speech recognition」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル