Title | ||
---|---|---|
Attribute Knowledge Integration For Speech Recognition Based On Multi-Task Learning Neural Networks |
Abstract | ||
---|---|---|
It has been demonstrated that the speech recognition performance can be improved by adding extra articulatory information, and subsequently, how to use such information effectively becomes a challenging problem. In this paper, we propose an attribute-based knowledge integration architecture which is realized by modeling and learning both acoustic and articulatory cues simultaneously in a uniform framework. The framework promotes the performance by providing attribute-based knowledge in both feature and model domains. In model domain, the attribute classification is used as the secondary task to improve the performance of an MTL-DNN used for speech recognition by lifting the discriminative ability on pronunciation. In feature domain, an attribute-based feature is extracted from an MTL-DNN trained with attribute classification as its primary task and phonetic/tri-phone state classification as the secondary task. Experiments on TIMIT and WSJ corpuses show that the proposed framework achieves significant performance improvements compared with the baseline DNN-HMM systems. |
Year | Venue | Keywords |
---|---|---|
2015 | 16TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2015), VOLS 1-5 | multi-task learning, automatic attribute transcription, deep neural networks |
Field | DocType | Citations |
Knowledge integration,Multi-task learning,Pattern recognition,Computer science,Speech recognition,Time delay neural network,Artificial intelligence,Deep learning,Artificial neural network | Conference | 1 |
PageRank | References | Authors |
0.38 | 4 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Hao Zheng | 1 | 10 | 3.29 |
Zhanlei Yang | 2 | 31 | 7.77 |
Liwei Qiao | 3 | 3 | 0.73 |
Jianping Li | 4 | 455 | 76.28 |
Wenju Liu | 5 | 214 | 39.32 |