Recurrent deep neural networks for robust speech recognition

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

Abstract

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 2 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">nd</sup> 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.
BibTeX
@inproceedings{weng2014recurrent,
  author = {Chao Weng and Dong Yu and Shinji Watanabe and Biing-Hwang Fred Juang},
  title = {{Recurrent deep neural networks for robust speech recognition}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2014},
  doi = {10.1109/icassp.2014.6854661},
}

Loading related content...

Figure