Recurrent deep neural networks for robust speech recognition

Chao Weng, Dong Yu, Shinji Watanabe, Biing Hwang Fred Juang

研究成果: Conference contribution

85 被引用数 (Scopus)

抄録

In this work, we propose recurrent deep neural networks (DNNs) for robust automatic speech recognition (ASR). Full recurrent connections are added to certain hidden layer of a conventional feedforward DNN and allow the model to capture the temporal dependency in deep representations. A new backpropagation through time (BPTT) algorithm is introduced to make the minibatch stochastic gradient descent (SGD) on the proposed recurrent DNNs more efficient and effective. We evaluate the proposed recurrent DNN architecture under the hybrid setup on both the 2nd CHiME challenge (track 2) and Aurora-4 tasks. Experimental results on the CHiME challenge data show that the proposed system can obtain consistent 7% relative WER improvements over the DNN systems, achieving state-of-the-art performance without front-end preprocessing, speaker adaptive training or multiple decoding passes. For the experiments on Aurora-4, the proposed system achieves 4% relative WER improvement over a strong DNN baseline system.

本文言語English
ホスト出版物のタイトル2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014
出版社Institute of Electrical and Electronics Engineers Inc.
ページ5532-5536
ページ数5
ISBN(印刷版)9781479928927
DOI
出版ステータスPublished - 2014 1 1
外部発表はい
イベント2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014 - Florence, Italy
継続期間: 2014 5 42014 5 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

Conference

Conference2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014
CountryItaly
CityFlorence
Period14/5/414/5/9

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

フィンガープリント 「Recurrent deep neural networks for 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