中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
Language-Adversarial Transfer Learning for Low-Resource Speech Recognition

文献类型:期刊论文

作者Yi, Jiangyan; Tao, Jianhua; Wen, Zhengqi; Bai, Ye
刊名IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING
出版日期2019-03-01
卷号27期号:3页码:621-630
关键词Adversarial training transfer learning cross-lingual low-resource speech recognition
ISSN号2329-9290
DOI10.1109/TASLP.2018.2889606
通讯作者Tao, Jianhua(jhtao@nlpr.ia.ac.cn)
英文摘要The 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.
WOS关键词DEEP NEURAL-NETWORKS ; ACOUSTIC MODELS
资助项目National 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]
WOS研究方向Acoustics ; Engineering
语种英语
WOS记录号WOS:000457913900001
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
资助机构National Key Research and Development Plan of China ; National Natural Science Foundation of China (NSFC) ; Inria-CAS Joint Research Project
源URL[http://ir.ia.ac.cn/handle/173211/25289]  
专题模式识别国家重点实验室_智能交互
通讯作者Tao, Jianhua
作者单位Chinese Acad Sci, Natl Lab Pattern Recognit, Inst Automat, Beijing 100190, Peoples R China
推荐引用方式
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.

入库方式: OAI收割

来源:自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。