Full-Text Search:
Home|Journal Papers|About CNKI|User Service|FAQ|Contact Us|中文
《Journal of Shanghai Jiaotong University》 2005-S1
Add to Favorite Get Latest Update

Discriminative Speaker Adaptation Based on Structural Eigenvoice Model

CAI Tie, ZHU Jie(Dept. of Electronic Eng., Shanghai Jiaotong Univ., Shanghai 200030, China)  
Regarding the drawbacks of eigenvoice speaker adaptation, a novel adaptation algorithm was proposed, which is called discriminative structural eigenvoice(DSEV). This algorithm can adjust the adaptation parameters with the available amount of adaptation data and discriminatively estimate them under the maximum mutual information(MMI) criterion, which further improves the adaptation performance. It can be shown from the experimental results of supervised adaptation that this algorithm achieves 6.7% relative reduction in error rate with only one adaptation sentence. The proposed method also shows better gradual improvement than eigenvoice with increased amount of adaptation data.
【Fund】: 上海市科学技术委员会基础研究项目基金(01JC14033)。
【CateGory Index】: TN912.34
Download(CAJ format) Download(PDF format)
CAJViewer7.0 supports all the CNKI file formats; AdobeReader only supports the PDF format.
【Citations】
Chinese Journal Full-text Database 1 Hits
1 LU Ping, WU Ji, WANG Zuoying, LU Dajin(Department of Electronic Engineering, Tsinghua University, BeiJing 100084, China);Rapid speaker adaptation for continuous speech recognition[J];Journal of Tsinghua University(Science and Technology);2002-07
【Co-citations】
Chinese Journal Full-text Database 2 Hits
1 PIAO Chun-jun,LI Yu-ping,HAN Yong-cheng (Institute of Electric Engineering,Yanshan University,Qinhuangdao 066004,China);Speaker adaptation algorithm based on eigen voice[J];Information Technology;2007-08
2 CAI Tie,ZHU Jie(Dept.of Electronic Eng.,Shanghai Jiaotong Univ.,Shanghai 200030,China);A Rapid Speaker Adaptation Based on Support Speaker Weighting[J];Journal of Shanghai Jiaotong University;2005-12
©2006 Tsinghua Tongfang Knowledge Network Technology Co., Ltd.(Beijing)(TTKN) All rights reserved