CASIA OpenIR
Language-Adversarial Transfer Learning for Low-Resource Speech Recognition
Yi, Jiangyan; Tao, Jianhua; Wen, Zhengqi; Bai, Ye
Source PublicationIEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING
ISSN2329-9290
2019-03-01
Volume27Issue:3Pages:621-630
Corresponding AuthorTao, Jianhua(jhtao@nlpr.ia.ac.cn)
AbstractThe acoustic model trained using the knowledge from the shared hidden layer (SHL) model outperforms the model trained only by using the target language, especially under low resource conditions. However, the shared features may contain some unnecessary language dependent information. It will degrade the performance of the target model. Therefore, this paper proposes language-adversarial transfer learning to alleviate this problem. Adversarial learning is used to ensure that the shared layers of the SHL-model can learn more language invariant features. Experiments are conducted on IARPA Babel datasets. The results show that the target model trained using the knowledge transferred from the adversarial SHL-model achieves up to 10.1% relative word error rate reduction when compared with the target model trained using the knowledge transferred from the SHL-model.
KeywordAdversarial training transfer learning cross-lingual low-resource speech recognition
DOI10.1109/TASLP.2018.2889606
WOS KeywordDEEP NEURAL-NETWORKS ; ACOUSTIC MODELS
Indexed BySCI
Language英语
Funding ProjectNational Key Research and Development Plan of China[2017YFC0820602] ; National Natural Science Foundation of China (NSFC)[61425017] ; National Natural Science Foundation of China (NSFC)[61773379] ; National Natural Science Foundation of China (NSFC)[61603390] ; National Natural Science Foundation of China (NSFC)[61771472] ; Inria-CAS Joint Research Project[173211KYSB20170061]
Funding OrganizationNational Key Research and Development Plan of China ; National Natural Science Foundation of China (NSFC) ; Inria-CAS Joint Research Project
WOS Research AreaAcoustics ; Engineering
WOS SubjectAcoustics ; Engineering, Electrical & Electronic
WOS IDWOS:000457913900001
PublisherIEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Citation statistics
Cited Times:1[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/25290
Collection中国科学院自动化研究所
Corresponding AuthorTao, Jianhua
AffiliationChinese Acad Sci, Natl Lab Pattern Recognit, Inst Automat, Beijing 100190, Peoples R China
First Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Corresponding Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Yi, Jiangyan,Tao, Jianhua,Wen, Zhengqi,et al. Language-Adversarial Transfer Learning for Low-Resource Speech Recognition[J]. IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING,2019,27(3):621-630.
APA Yi, Jiangyan,Tao, Jianhua,Wen, Zhengqi,&Bai, Ye.(2019).Language-Adversarial Transfer Learning for Low-Resource Speech Recognition.IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING,27(3),621-630.
MLA Yi, Jiangyan,et al."Language-Adversarial Transfer Learning for Low-Resource Speech Recognition".IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING 27.3(2019):621-630.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Yi, Jiangyan]'s Articles
[Tao, Jianhua]'s Articles
[Wen, Zhengqi]'s Articles
Baidu academic
Similar articles in Baidu academic
[Yi, Jiangyan]'s Articles
[Tao, Jianhua]'s Articles
[Wen, Zhengqi]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Yi, Jiangyan]'s Articles
[Tao, Jianhua]'s Articles
[Wen, Zhengqi]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

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