Probabilistic feature transformation for channel robust speaker verification

Man Wai Mak, Kwok Kwong Yiu

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

Abstract

Feature transformation plays an important role in robust speaker verification over telephone networks. This paper compares several feature transformation techniques and evaluates their verification performance and computation time under the 2000 NIST speaker recognition evaluation protocol. Techniques compared include feature mapping (FM), stochastic feature transformation (SFT), and blind stochastic feature transformation (BSFT). The paper proposes a probabilistic feature mapping (PFM) in which the mapped features depend not only on the top-1 decoded Gaussian but also on the posterior probabilities of other Gaussians in the root model. The paper also proposes speeding up the computation of PFM and BSFT parameters by considering the top few Gaussians only. Results show that PFM performs slightly better than FM and that the fast approach can reduce computation time substantially. Among the approaches investigated, the fast BSFT is found to have the highest potential for robust speaker verification over telephone networks because it can achieve good performance without any a priori knowledge of the communication channel. It was also found that fusion of the scores derived from systems using BSFT and PFM can reduce the error rate further.
Original languageEnglish
Title of host publicationProceedings of the 2006 16th IEEE Signal Processing Society Workshop on Machine Learning for Signal Processing, MLSP 2006
Pages433-438
Number of pages6
DOIs
Publication statusPublished - 1 Dec 2007
Event2006 16th IEEE Signal Processing Society Workshop on Machine Learning for Signal Processing, MLSP 2006 - Maynooth, Ireland
Duration: 6 Sept 20068 Sept 2006

Conference

Conference2006 16th IEEE Signal Processing Society Workshop on Machine Learning for Signal Processing, MLSP 2006
Country/TerritoryIreland
CityMaynooth
Period6/09/068/09/06

ASJC Scopus subject areas

  • Artificial Intelligence
  • Software
  • Signal Processing

Fingerprint

Dive into the research topics of 'Probabilistic feature transformation for channel robust speaker verification'. Together they form a unique fingerprint.

Cite this