Show simple item record

dc.contributor.authorMagrin-Chagnolleau, Ivan
Bonastre, Jean-Francois
Bimbot, Frederic
dc.creatorMagrin-Chagnolleau, Ivan
Bonastre, Jean-Francois
Bimbot, Frederic
dc.date.accessioned 2007-10-31T00:52:09Z
dc.date.available 2007-10-31T00:52:09Z
dc.date.issued 1995-01-01
dc.date.submitted 1995-01-01
dc.identifier.urihttps://hdl.handle.net/1911/20072
dc.description Conference Paper
dc.description.abstract Second-order statistical methods show very good results for automatic speaker identification in controlled recording conditions. These approaches are generally used on the entire speech material available. In this paper, we study the influence of the content of the test speech material on the performances of such methods, i.e. under a more analytical approach. The goal is to investigate on the kind of information which is used by these methods, and where it is located in the speech signal. Liquids and glides together, vowels, and more particularly nasal vowels and nasal consonants, are found to be particularly speaker specific: test utterances of 1 second, composed in majority of acoustic material from one of these classes provide better speaker identification results than phonetically balanced test utterances, even though the training is done, in both cases, with 15 seconds of phonetically balanced speech. Nevertheless, results with other phoneme classes are never dramatically poor. These results tend to show that the speaker-dependent information captured by long-term second-order statistics is consistently common to all phonetic classes, and that the homogeneity of the test material may improve the quality of the estimates.
dc.language.iso eng
dc.subjectTemporary
dc.subject.otherGeneral DSP
dc.title Effect of Utterance Duration and Phonetic Content on Speaker Identification Usind Second Order Statistical Methods
dc.type Conference paper
dc.date.note 2004-01-14
dc.citation.bibtexName inproceedings
dc.date.modified 2004-11-05
dc.contributor.orgDigital Signal Processing (http://dsp.rice.edu/)
dc.subject.keywordTemporary
dc.citation.conferenceName Proceedings of EUROSPEECH
dc.type.dcmi Text
dc.type.dcmi Text
dc.identifier.citation I. Magrin-Chagnolleau, J. Bonastre and F. Bimbot, "Effect of Utterance Duration and Phonetic Content on Speaker Identification Usind Second Order Statistical Methods," 1995.


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

  • DSP Publications [508]
    Publications by Rice Faculty and graduate students in digital signal processing.
  • ECE Publications [1289]
    Publications by Rice University Electrical and Computer Engineering faculty and graduate students

Show simple item record