Research on Intersession Variability Compensation for MLLR-SVM Speaker Recognition | |
Zhong, Shan ; Shan, Yuxiang ; He, Liang ; Liu, Jia | |
2010-10-12 ; 2010-10-12 | |
关键词 | speaker recognition intersession variability MLLR SVM VERIFICATION Computer Science, Hardware & Architecture Computer Science, Information Systems Engineering, Electrical & Electronic |
中文摘要 | One of the most important challenges in speaker recognition is intersession variability (ISV), primarily cross-channel effects. Recent NIST speaker recognition evaluations (SRE) include a multilingual scenario with training conversations involving multilingual speakers collected in a number of other languages, leading to further performance decline. One important reason for this is that more and more researchers are using phonetic clustering to introduce high level information to improve speaker recognition. But such language dependent methods do not work well in multilingual conditions. In this paper, we study both language and channel mismatch using a support vector machine (SVM) speaker recognition system. Maximum likelihood linear regression (MLLR) transforms adapting a universal background model (UBM) are adopted as features. We first introduce a novel language independent statistical binary-decision tree to reduce multi-language effects, and compare this data-driven approach with a traditional knowledge based one. We also construct a framework for channel compensation using feature-domain latent factor analysis (LFA) and MLLR supervector kernel-based nuisance attribute projection (NAP) in the model-domain. Results on the NIST SRE 2006 1conv4w-1conv4w/mic corpus show significant improvement. We also compare our compensated MLLR-SVM system with state-of-the-art cepstral Gaussian mixture and SVM systems, and combine them for a further improvement. |
语种 | 英语 ; 英语 |
出版者 | IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG ; TOKYO ; KIKAI-SHINKO-KAIKAN BLDG MINATO-KU SHIBAKOEN 3 CHOME, TOKYO, 105, JAPAN |
内容类型 | 期刊论文 |
源URL | [http://hdl.handle.net/123456789/82418] |
专题 | 清华大学 |
推荐引用方式 GB/T 7714 | Zhong, Shan,Shan, Yuxiang,He, Liang,et al. Research on Intersession Variability Compensation for MLLR-SVM Speaker Recognition[J],2010, 2010. |
APA | Zhong, Shan,Shan, Yuxiang,He, Liang,&Liu, Jia.(2010).Research on Intersession Variability Compensation for MLLR-SVM Speaker Recognition.. |
MLA | Zhong, Shan,et al."Research on Intersession Variability Compensation for MLLR-SVM Speaker Recognition".(2010). |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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。
修改评论