We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
基于混合DBNN-BLSTM模型的大词汇量连续语音识别.
- Authors
李云红; 王 成; 王延年
- Abstract
The recognition rate is not ideal when the feature extraction is performed on the deep confidence neural network(DBNN)model and the bidirectional long-short term memory(BLSTM), the long-short term memory(LSTM)and BLSTM can better analyze the characteristics of speech data. By combining the DBNN model with BLSTM, a new acoustic modeling method for large vocabulary continuous speech recognition(LVCSR)is proposed and experimentally studied based on Keras deep learning framework. The experimental results show that the improved DBNN-BLSTM model has a high recognition accuracy, and improved 5% more than BLSTM.
- Publication
Basic Sciences Journal of Textile Universities / Fangzhi Gaoxiao Jichu Kexue Xuebao, 2018, Vol 31, Issue 1, p103
- ISSN
1006-8341
- Publication type
Article
- DOI
10.13338/j.issn.1006-8341.2018.01.017