CASIA OpenIR  > 模式识别国家重点实验室  > 机器人视觉
Attribute Knowledge Integration for Speech Recognition Based on Multi-task Learning Neural Networks
Hao Zheng1; Zhanlei Yang1; Liwei Qiao2; Jianping Li2; Wenju Liu1
2015
Conference NameINTERSPEECH
Source PublicationINTERSPEECH
Conference Date2015
Conference PlaceDresden, Germany
AbstractIt 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.
KeywordMulti-task Learning Automatic Attribute Transcription Deep Neural Networks
Indexed ByEI
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/11779
Collection模式识别国家重点实验室_机器人视觉
Corresponding AuthorHao Zheng
Affiliation1.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences
2.Electric Power Research Institute of Shanxi Electric Power Company
Recommended Citation
GB/T 7714
Hao Zheng,Zhanlei Yang,Liwei Qiao,et al. Attribute Knowledge Integration for Speech Recognition Based on Multi-task Learning Neural Networks[C],2015.
Files in This Item: Download All
File Name/Size DocType Version Access License
IS-2015-1.pdf(388KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Hao Zheng]'s Articles
[Zhanlei Yang]'s Articles
[Liwei Qiao]'s Articles
Baidu academic
Similar articles in Baidu academic
[Hao Zheng]'s Articles
[Zhanlei Yang]'s Articles
[Liwei Qiao]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Hao Zheng]'s Articles
[Zhanlei Yang]'s Articles
[Liwei Qiao]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: IS-2015-1.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.