Cluster-dependent feature transformation with divergence-based out-of-handset rejection for robust speaker verification

Chi Leung Tsang, Man Wai Mak, Sun Yuan Kung

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

Abstract

This paper proposes a divergence-based cluster selector with out-of-handset (OOH) rejection capability to identify the 'unseen' handsets. This is achieved by measuring the Jensen difference between the selector's output and a constant vector with identical elements. The resulting cluster selector is combined with a feature-based channel compensation algorithm for telephone-based speaker verification. Utterances whose handsets are identified as 'unseen' will be normalized by cepstral mean subtraction (CMS). On the other hand, if the handset can be identified (considered as 'seen'), a corresponding set of cluster-dependent transformation parameters will be used to transform the utterances. Experiments based on ten handsets of the HTIMIT corpus show that using the cluster-dependent transformation parameters to transform the utterances with correctly identified handsets and processing those utterances with 'unseen' handsets by CMS achieve the best result.

Original languageEnglish (US)
Title of host publicationICICS-PCM 2003 - Proceedings of the 2003 Joint Conference of the 4th International Conference on Information, Communications and Signal Processing and 4th Pacific-Rim Conference on Multimedia
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1399-1403
Number of pages5
ISBN (Electronic)0780381858, 9780780381858
DOIs
StatePublished - Jan 1 2003
EventJoint Conference of the 4th International Conference on Information, Communications and Signal Processing and 4th Pacific-Rim Conference on Multimedia, ICICS-PCM 2003 - Singapore, Singapore
Duration: Dec 15 2003Dec 18 2003

Publication series

NameICICS-PCM 2003 - Proceedings of the 2003 Joint Conference of the 4th International Conference on Information, Communications and Signal Processing and 4th Pacific-Rim Conference on Multimedia
Volume3

Other

OtherJoint Conference of the 4th International Conference on Information, Communications and Signal Processing and 4th Pacific-Rim Conference on Multimedia, ICICS-PCM 2003
CountrySingapore
CitySingapore
Period12/15/0312/18/03

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Signal Processing
  • Media Technology

Fingerprint Dive into the research topics of 'Cluster-dependent feature transformation with divergence-based out-of-handset rejection for robust speaker verification'. Together they form a unique fingerprint.

  • Cite this

    Tsang, C. L., Mak, M. W., & Kung, S. Y. (2003). Cluster-dependent feature transformation with divergence-based out-of-handset rejection for robust speaker verification. In ICICS-PCM 2003 - Proceedings of the 2003 Joint Conference of the 4th International Conference on Information, Communications and Signal Processing and 4th Pacific-Rim Conference on Multimedia (pp. 1399-1403). [1292695] (ICICS-PCM 2003 - Proceedings of the 2003 Joint Conference of the 4th International Conference on Information, Communications and Signal Processing and 4th Pacific-Rim Conference on Multimedia; Vol. 3). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICICS.2003.1292695