Building DNN acoustic models for large vocabulary speech recognition
详细信息 查看全文
- 作者：Andrew L. Maas ; amaas@cs.stanford.edu" class="auth_mail" title="E-mail the corresponding author ; Peng Qi ; Ziang Xie ; Awni Y. Hannun ; Christopher T. Lengerich ; Daniel Jurafsky ; Andrew Y. Ng
- 关键词：Hidden Markov model deep neural network (HMM-DNN) ; Neural networks ; Acoustic modeling ; Speech recognition ; Large vocabulary continuous speech recognition (LVCSR)
- 刊名：Computer Speech & Language
- 出版年：2017
- 出版时间：January 2017
- 年：2017
- 卷：41
- 期：Complete
- 页码：195-213
- 全文大小：685 K
文摘
- •
Empirical investigation of neural network acoustic models for speech recognition.
- •
Evaluation of DNNs up to ten times larger than those used in previous works.
- •
Comparison of densely connected, convolutional, and locally-connected untied neural networks.
- •
Results on Switchboard and a combined 2100 hour corpus.
- •
Explanation of combined corpus baseline system training recipe which is now a part of the Kaldi speech toolkit.