自动化学报2011，Vol.37Issue(12)：1495-1502,8.DOI:10.3724/SP.J.1004.2011.01495
一种新的基于子空间的说话人自适应方法
A New Subspace Based Speaker Adaptation Method
摘要
Abstract
A new speaker adaptation method based on subspace modeling is proposed. After performing eigen-voice (EV) analysis and finding the speaker subspace, another low dimensional subspace is found in the phone space. The new subspace can capture the inter-speaker variability as well as intra-speaker variability of the hidden Markov model (HMM) model parameters. This joint speaker-phone subspace is both robust and compact. In large vocabulary continuous speech recognition experiments, the new method showed better unsupervised adaptation than the baseline maximum likelihood linear regression and clustered maximum-likelihood linear basis adaptation method, especially when the adaptation data were less than 30 s.关键词
连续语音识别/说话人自适应/本征音/本征音子Key words
Continuous speech recognition,speaker adaptation,eigen-voice (EV), eigen-phone (EP)引用本文复制引用
张文林,张卫强,刘加,李弼程,屈丹..一种新的基于子空间的说话人自适应方法[J].自动化学报,2011,37(12):1495-1502,8.基金项目
国家自然科学基金(60872142,61005019,61175017)资助 （60872142,61005019,61175017）
