A variable frame length and rate algorithm based on the spectral kurtosis measure for speaker verification

Chi Sang Jung, Kyu J. Han, Hyunson Seo, Shrikanth S. Narayanan, Hong Goo Kang

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

8 Citations (Scopus)

Abstract

In this paper, we propose a spectral kurtosis based approach to extract features with a variable frame length and rate for speaker verification. Since the speaker-specific information of features in each frame changes depending upon the characteristics of speech, it is important to determine the appropriate frame length and rate to extract the salient feature frames. In order to distinctively represent the characteristics of vowels and consonants both in time and frequency domains, we introduce a variable frame length and rate (VFLR) method based on spectral kurtosis, which provides a local measure of time-frequency concentration. Experimental results verify that the proposed VFLR method improves the performance of the speaker verification system on the NIST SRE-06 database by 9.725% (relative) compared to the feature extraction method with the fixed length and rate.

Original languageEnglish
Title of host publicationProceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010
PublisherInternational Speech Communication Association
Pages2754-2757
Number of pages4
Publication statusPublished - 2010

Publication series

NameProceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010

All Science Journal Classification (ASJC) codes

  • Language and Linguistics
  • Speech and Hearing

Fingerprint

Dive into the research topics of 'A variable frame length and rate algorithm based on the spectral kurtosis measure for speaker verification'. Together they form a unique fingerprint.

Cite this