The effect of GMM order and CMS on speaker recognition with reverberant speech

Noam R. Shabtai, Yaniv Zigel, Boaz Rafaely

Research output: Contribution to conferencePaperpeer-review

7 Scopus citations

Abstract

Speaker recognition is used today in a wide range of applications. The presence of reverberation, in hands-free systems for example, results in performance degradation. The effect of reverberation on the feature vectors and its relation to optimal GMM order are investigated. Optimal model order is calculated in terms of minimum BIC and KIC, and tested for EER of a GMM-based speaker recognition system. Experimental results show that for high reverberation time, reducing model order reduces EER values of speaker recognition. The effect of CMS on state of the art GMM and AGMM-based speaker recognition systems is investigated for reverberant speech. Results show that high reverberation time reduces the effectiveness of CMS.

Original languageEnglish
Pages144-147
Number of pages4
DOIs
StatePublished - 3 Sep 2008
Event2008 Hands-free Speech Communication and Microphone Arrays, HSCMA 2008 - Trento, Italy
Duration: 6 May 20088 May 2008

Conference

Conference2008 Hands-free Speech Communication and Microphone Arrays, HSCMA 2008
Country/TerritoryItaly
CityTrento
Period6/05/088/05/08

Keywords

  • Cepstral mean subtraction
  • Gaussian mixture model
  • Model order
  • Reverberation
  • Speaker recognition

Fingerprint

Dive into the research topics of 'The effect of GMM order and CMS on speaker recognition with reverberant speech'. Together they form a unique fingerprint.

Cite this