Conference paper

KOCKMANN Marcel, FERRER Luciana, BURGET Lukáš, SHRIBERG Elisabeth and ČERNOCKÝ Jan. Recent Progress in Prosodic Speaker Verification. In: Proceedings of the 2011 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011. Praha: IEEE Signal Processing Society, 2011, pp. 4556-4559. ISBN 978-1-4577-0537-3.
Publication language:english
Original title:Recent Progress in Prosodic Speaker Verification
Title (cs):Aktuální pokrok v prosodickém ověřování mluvčího
Pages:4556-4559
Proceedings:Proceedings of the 2011 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011
Conference:International Conference on Acoustics, Speech and Signal Processing 2011
Place:Praha, CZ
Year:2011
ISBN:978-1-4577-0537-3
Publisher:IEEE Signal Processing Society
URL:http://www.fit.vutbr.cz/research/groups/speech/publi/2011/kockmann_icassp2011_4556.pdf [PDF]
Keywords
Prosodic speaker verification, SNERFs, MSM, iVector, PLDA
Annotation
We have proposed a technique for modeling complex prosodic features, such as SNERFs, using a multinomial subspace model for feature extraction and probabilistic linear discriminant analysis for session variability compensation.
Abstract
We describe recent progress in the field of prosodic modeling for speaker verification. In a previous paper, we proposed a technique for modeling syllable-based prosodic features that uses a multinomial subspace model for feature extraction and within-class covariance normalization or linear discriminant analysis for session variability compensation. In this paper, we show that performance can be significantly improved with the use of probabilistic linear discriminant analysis (PLDA) for session variability compensation. This system does not require score normalization. We report an equal error rate below 7% on a NIST 2008 task. To our knowledge, this is the best reported result to date for a prosodic system for speaker recognition. Fusion of this system with a state-of-the-art acoustic baseline system yields 10% relative improvement in the new detection cost function (DCF) as defined by NIST.
BibTeX:
@INPROCEEDINGS{
   author = {Marcel Kockmann and Luciana Ferrer and Lukáš Burget and
	Elisabeth Shriberg and Jan Černocký},
   title = {Recent Progress in Prosodic Speaker Verification},
   pages = {4556--4559},
   booktitle = {Proceedings of the 2011 IEEE International Conference on
	Acoustics, Speech, and Signal Processing, ICASSP 2011},
   year = {2011},
   location = {Praha, CZ},
   publisher = {IEEE Signal Processing Society},
   ISBN = {978-1-4577-0537-3},
   language = {english},
   url = {http://www.fit.vutbr.cz/research/view_pub.php?id=9656}
}

Your IPv4 address: 54.211.68.132
Switch to IPv6 connection

DNSSEC [dnssec]