Show simple item record

dc.contributor.authorBimbot, Frederic
Magrin-Chagnolleau, Ivan
dc.creatorBimbot, Frederic
Magrin-Chagnolleau, Ivan
dc.date.accessioned 2007-10-31T00:37:19Z
dc.date.available 2007-10-31T00:37:19Z
dc.date.issued 1995-08-20
dc.date.submitted 1995-08-20
dc.identifier.urihttp://hdl.handle.net/1911/19736
dc.description Conference Paper
dc.description.abstract This article presents an overview of several measures for speaker recognition. These measures relate to second-order statistical tests, and can be expressed under a common formalism. Alternate formulations of these measures are given and their mathematical properties are studied. In their basic form, these measures are asymmetric, but they can be symmetrized in various ways. All measures are tested in the framework of text-independent closed-set speaker identification, on 3 variants of the TIMIT database (630 speakers) : TIMIT (high quality speech), FTIMIT (a restricted bandwidth version of TIMIT) and NTIMIT (telephone quality). Remarkable performances are obtained on TIMIT but the results naturally deteriorate with FTIMIT and NTIMIT. Symmetrization appears to be a factor of improvement, especially when little speech material is available. The use of some of the proposed measures as a reference benchmark to evaluate the intrinsic complexity of a given database under a given protocol is finally suggested as a conclusion to this work.
dc.language.iso eng
dc.subjectTemporary
dc.subject.otherSignal Processing Applications
dc.title Second-Order Statistical Measures for Text-Independent Speaker Identification
dc.type Conference paper
dc.date.note 2004-01-14
dc.citation.bibtexName inproceedings
dc.date.modified 2004-01-22
dc.contributor.orgDigital Signal Processing (http://dsp.rice.edu/)
dc.subject.keywordTemporary
dc.citation.conferenceName Speech Communication
dc.type.dcmi Text
dc.type.dcmi Text
dc.identifier.doihttp://dx.doi.org/10.1016/0167-6393(95)00013-E
dc.identifier.citation F. Bimbot and I. Magrin-Chagnolleau, "Second-Order Statistical Measures for Text-Independent Speaker Identification," 1995.


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

  • ECE Publications [1212]
    Publications by Rice University Electrical and Computer Engineering faculty and graduate students
  • DSP Publications [508]
    Publications by Rice Faculty and graduate students in digital signal processing.

Show simple item record