Result Details

Syllable based Feature-Contours for Speaker Recognition

KOCKMANN, M.; BURGET, L. Syllable based Feature-Contours for Speaker Recognition. Proc. 14th International Workshop on Advances in Speech Technology. Maribor: 2008. p. 1-4.
Type
conference paper
Language
English
Authors
Kockmann Marcel, Dipl.-Ing., Ph.D.
Burget Lukáš, doc. Ing., Ph.D., DCGM (FIT)
Abstract

the paper is on Syllable based Feature-Contours for Speaker Recognition

Keywords

speaker recognition

URL
Annotation

The use of acoustic short-time features for speaker identification has established itself for several years. In this work, classical acoustic as well as prosodic features are jointly used in a lexical context. The contours of pitch, energy and cepstral coeffi- cients are continuously modeled over the time span of a syllable to capture the speaking style on phonetic level. Especially the addition of cepstral contours highly improves the performance. Due to the small amount of data, best results are achieved with a factor analysis framework. Results are presented for the NIST SRE 2006 speaker identification task.

Published
2008
Pages
1–4
Proceedings
Proc. 14th International Workshop on Advances in Speech Technology
Conference
14th International Workshop on Advances in Speech Technology
Place
Maribor
BibTeX 
@inproceedings{BUT32070,
  author="Marcel {Kockmann} and Lukáš {Burget}",
  title="Syllable based Feature-Contours for Speaker Recognition",
  booktitle="Proc. 14th International Workshop on Advances in Speech Technology",
  year="2008",
  pages="1--4",
  address="Maribor",
  url="http://www.fit.vutbr.cz/research/groups/speech/publi/2008/kockmann_ast2008.pdf"
}
Projects
CARETAKER - Content Analysis and REtrieval Technologies to Apply Knowledge Extraction to massive Recording, EU, Sixth Framework programme, 027231, start: 2006-03-01, end: 2008-09-30, completed
Interactive Keyword Detector, GACR, Postdoktorandské granty, GP102/06/P383, start: 2006-01-01, end: 2008-12-31, completed
Mobile Biometry, MŠMT, Podpora projektů sedmého rámcového programu Evropského společenství pro výzkum, technologický rozvoj a demonstrace (2007 až 2013) podle zákona č. 171/2007 Sb., 7E08042, start: 2008-01-01, end: 2010-12-31, completed
Security-Oriented Research in Information Technology, MŠMT, Institucionální prostředky SR ČR (např. VZ, VC), MSM0021630528, start: 2007-01-01, end: 2013-12-31, running
Speech Recognition under Real-World Conditions, GACR, Standardní projekty, GA102/08/0707, start: 2008-01-01, end: 2011-12-31, completed
Research groups
Speech Data Mining Research Group BUT Speech@FIT (RG SPEECH)
Departments
Department of Computer Graphics and Multimedia (DCGM)
Back to top