Browse > Article

A Study on Channel Mis-match Compensation Technique for Robust Speaker Verification System  

강철호 (광운대학교 대학원 전자통신공학과)
정희석 (광운대학교 대학원 전자통신공학과)
Abstract
In this paper, we proposed the compensation technique that overcomes the limitations of the conventional approaches through summing up the bias terms between world's codebook and individual codebook vectors of feature parameters. But, mean compensation without condition can bring higher false acceptance. Therefore, the proposed technique compensates the channel mis-match condition by weighted bias sum using nonlinear function regarding to the distortion between speech and silence. The simulation results show that the FRR (flase reject rate) is decreased 14.95% when the proposed algorithm was applied.
Keywords
Mis-match compensation; Bias reduction; speaker verification;
Citations & Related Records
연도 인용수 순위
  • Reference
1 Microphone array based speech recognition with different talker-array positions /
[ M.Omologo;M.Matassoni;P.Svaizer;D.Giuliani ] / Proc. ICASSP97
2 Effectiveness of Linear Prediction Characteristics of the Speech Wave for Automatic Speaker Identification and Verification /
[ Atal,B.S. ] / Journal of the Acoustical Society of America
3 Pole-filtered cepstral mean subtraction /
[ D.Naik ] / Proceedings ICASSP-1995
4 Recent research in automatic speaker recognition /
[ A.E.Rosenberg;F.K.Soong ] / Advances in Speech Signal Processing
5 Robust speaker verification over the telephone by feature recuperation /
[ M.W.Mak;S.Y.Kung ] / Intelligent Multimedia, Video and Speech Processing, 2001 Proceedings of 2001 International Symposium on
6 Speaker Verification: A Turorial /
[ Jayant M. Naik ] / IEEE Communication Magazine