Deep long short-term memory adaptive beamforming networks for multichannel robust speech recognition

Zhong Meng, Shinji Watanabe, John R. Hershey, Hakan Erdogan

研究成果: Conference contribution

43 被引用数 (Scopus)

抄録

Far-field speech recognition in noisy and reverberant conditions remains a challenging problem despite recent deep learning breakthroughs. This problem is commonly addressed by acquiring a speech signal from multiple microphones and performing beamforming over them. In this paper, we propose to use a recurrent neural network with long short-term memory (LSTM) architecture to adaptively estimate real-time beamforming filter coefficients to cope with non-stationary environmental noise and dynamic nature of source and microphones positions which results in a set of timevarying room impulse responses. The LSTM adaptive beamformer is jointly trained with a deep LSTM acoustic model to predict senone labels. Further, we use hidden units in the deep LSTM acoustic model to assist in predicting the beamforming filter coefficients. The proposed system achieves 7.97% absolute gain over baseline systems with no beamforming on CHiME-3 real evaluation set.

本文言語English
ホスト出版物のタイトル2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings
出版社Institute of Electrical and Electronics Engineers Inc.
ページ271-275
ページ数5
ISBN(電子版)9781509041176
DOI
出版ステータスPublished - 2017 6 16
外部発表はい
イベント2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - New Orleans, United States
継続期間: 2017 3 52017 3 9

出版物シリーズ

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

Other

Other2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017
国/地域United States
CityNew Orleans
Period17/3/517/3/9

ASJC Scopus subject areas

  • ソフトウェア
  • 信号処理
  • 電子工学および電気工学

フィンガープリント

「Deep long short-term memory adaptive beamforming networks for multichannel robust 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