We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Optimization of deep neural network in acoustic modeling for mandarin speech recognition.
- Authors
XIAO Yeming; ZHANG Qingqing; SONG Liming; PAN Jielin; YAN Yonghong
- Abstract
The deep neural network (DNN) as acoustic model is introduced into the Mandarin Conversational Telephone Speech recognition system. Firstly, as the character error rate is high for the spontaneous speech recognition, started from the acoustic feature type selection, meta -- parameters tuning during training and the optimization of the model generalization capability, a series of optimizations have been implemented to the DNN based acoustic modeling. Secondly, a smoothing algorithm is proposed for the sparse distribution of the states prior probabilities in the training samples, with this algorithm the character error rate is reduced by 1 % absolutely. And finally, on our three conversational telephone speech test sets, the optimized -- DNN model achieves a consistent performance enhancement over the baseline-DNN model, the average relative character error rate decreases by 15%. This experimental results demonstrate that these optimized strategies can improve the performance of the DNN based acoustic models.
- Subjects
ARTIFICIAL neural networks; AUTOMATIC speech recognition; CHINESE character sets (Data processing); ERROR rates; ALGORITHMS; HIDDEN Markov models
- Publication
Journal of Chongqing University of Posts & Telecommunications (Natural Science Edition), 2014, Vol 26, Issue 3, p373
- ISSN
1673-825X
- Publication type
Article
- DOI
10.3979/j.issn.673-825X.2014.03.017