Publication Details

Contour modeling of prosodic and acoustic features for speaker recognition

KOCKMANN Marcel and BURGET Lukáš. Contour modeling of prosodic and acoustic features for speaker recognition. In: Proc. 2008 IEEE Workshop on Spoken Language Technology. Goa: IEEE Signal Processing Society, 2008, p. 4. ISBN 978-1-4244-3472-5.
Czech title
Modelování kontur akustických a prózodických parametrů v rozpoznávání řečníka
Type
conference paper
Language
english
Authors
Kockmann Marcel, Dipl.-Ing. (DCGM FIT BUT)
Burget Lukáš, doc. Ing., Ph.D. (DCGM FIT BUT)
URL
Keywords

Speaker recognition, Prosody, GMM, Channel Compensation

Abstract

The paper is on contour modeling of prosodic and acoustic features for speaker recognition

Annotation

In this paper we use acoustic and prosodic features jointly in a long temporal lexical context for automatic speaker recognition from speech. The contours of pitch, energy and cepstral coefficients are continuously modeled over the time span of a syllable to capture the speaking style on phonetic level. As these features are affected by session variability, established channel compensation techniques are examined. Results for the combination of different features on a syllable-level as well as for channel compensation are presented for the NIST SRE 2006 speaker identification task. To show the complementary
character of the features, the proposed system is fused with
an acoustic short-time system, leading to a relative improvement of 10:4%.

Published
2008
Pages
4
Proceedings
Proc. 2008 IEEE Workshop on Spoken Language Technology
Conference
2008 IEEE Workshop on Spoken Language Technology, Goa, IN
ISBN
978-1-4244-3472-5
Publisher
IEEE Signal Processing Society
Place
Goa, IN
BibTeX 
@INPROCEEDINGS{FITPUB8841,
   author = "Marcel Kockmann and Luk\'{a}\v{s} Burget",
   title = "Contour modeling of prosodic and acoustic features for speaker recognition",
   pages = 4,
   booktitle = "Proc. 2008 IEEE Workshop on Spoken Language Technology",
   year = 2008,
   location = "Goa, IN",
   publisher = "IEEE Signal Processing Society",
   ISBN = "978-1-4244-3472-5",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/8841"
}
Back to top