Eigenchannel Compensation and Symmetric Score for Robust Text-Independent Speaker Verification

Yuan Dong, Jian Zhao, Liang Lu, Jiqing Lui, Xianyu Zhao, Haila Wang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The negative effect of the session variability has become more and more severe for the performance of the speaker verification system. This paper discusses the eigenchannel compensation and investigates the symmetric scoring method to diminish the session variability and further enhance the performance. Experiments were conducted on the core tests of the 2006 and 2008 speaker recognition evaluation (SRE) corpuses of the national institute of standards and technology (NIST) respectively. The experimental results demonstrate that the eigenchannel compensation can achieve excellent improvement and the symmetric scoring, as a measurement of cross similarity, can further improve the performance moderately. Overall, the system performance can be significantly improved, with equal error rate from 9.74% to 5.08% , 47.8% on SRE06 corpus and from 16.26% to 9.42% , 42.1% on SRE08 corpus while detection cost function from 0.0456 to 0.0263 , 42.3% on SRE06 corpus and from 0.0692 to 0.0449 , 35.1% on SRE08 corpus.
Original languageEnglish
Title of host publicationChinese Spoken Language Processing, 2008. ISCSLP '08. 6th International Symposium on
EditorsHelen Meng, Hui Jiang, Jianhua Tao, Ren-hua Wang
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages1-4
Number of pages4
ISBN (Electronic)978-1-4244-2943-1
ISBN (Print)978-1-4244-2942-4
DOIs
Publication statusPublished - 1 Dec 2008
Event2008 6th International Symposium on Chinese Spoken Language Processing - Kunming, China
Duration: 16 Dec 200819 Dec 2008

Symposium

Symposium2008 6th International Symposium on Chinese Spoken Language Processing
CountryChina
CityKunming
Period16/12/0819/12/08

Keywords

  • eigenvalues and eigenfunctions
  • speaker recognition
  • Eigenchannel compensation
  • equal error rate
  • robust text independent
  • session variability
  • speaker verification
  • symmetric scoring method
  • Acoustic testing
  • Error analysis
  • Loudspeakers
  • Maximum likelihood estimation
  • NIST
  • Robustness
  • Speaker recognition
  • Speech synthesis
  • System performance
  • Telecommunications

Fingerprint Dive into the research topics of 'Eigenchannel Compensation and Symmetric Score for Robust Text-Independent Speaker Verification'. Together they form a unique fingerprint.

Cite this