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 |
| DOI | 10.1109/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。