An investigation of sub-band FM feature extraction in speaker recognition

  • T. Thiruvaran
  • , J. Epps
  • , E. Ambikairajah
  • , E. Jones

Research output: Chapter in Book or Conference Publication/ProceedingConference Publicationpeer-review

1 Citation (Scopus)

Abstract

Following recent evidence that FM features extracted from a sub-band decomposition of speech are highly uncorrelated, this paper investigates the effect of the number of auditory scale sub-bands in FM based front-end processing. For this study, a newly developed robust FM extraction method based on the least square differential ratio is used to extract features, comprising one FM component per sub-band. Automatic speaker recognition experiments were conducted on the cellular NIST 2001 database, with the number of filters in the front-end varied from 6 to 26. Performance degradation was observed for very low numbers of filters and very high numbers of filters. Results show that for a 4 kHz speech bandwidth, a minimum of 10 and a maximum of 18 sub-bands is a suitable choice for speech front-end applications such as automatic speaker recognition.

Original languageEnglish
Title of host publicationIET Irish Signals and Systems Conference, ISSC 2008
Pages32-36
Number of pages5
Edition539 CP
DOIs
Publication statusPublished - 2008
EventIET Irish Signals and Systems Conference, ISSC 2008 - Galway, Ireland
Duration: 18 Jun 200819 Jun 2008

Publication series

NameIET Conference Publications
Number539 CP

Conference

ConferenceIET Irish Signals and Systems Conference, ISSC 2008
Country/TerritoryIreland
CityGalway
Period18/06/0819/06/08

Keywords

  • Automatic speaker recognition
  • Filter bank
  • Frequency modulation
  • Mel scale

Fingerprint

Dive into the research topics of 'An investigation of sub-band FM feature extraction in speaker recognition'. Together they form a unique fingerprint.

Cite this