Discriminative training for speaker identification based on maximum model distance algorithm

Q. Y. HONG*, S. KWONG

*Corresponding author for this work

Research output: Book Chapters | Papers in Conference ProceedingsConference paper (refereed)Researchpeer-review

6 Citations (Scopus)

Abstract

In this paper we apply the Maximum model distance (MMD) training to speaker identification and a new selection strategy of competitive speakers is proposed to it. The traditional ML method only utilizes the utterances for each speaker model, which probably leads to a local optimization solution. By maximizing the dissimilarities among those similar speaker models, MMD could add the discriminative capability into the training procedure and then improve the identification performance. Based on the TIMIT corpus, we designed the word and sentence experiments to evaluate this proposed training approach. The results show that the identification performance can be improved greatly when the training data is limited.

Original languageEnglish
Title of host publicationProceedings of the 2004 IEEE International Conference on Acoustics, Speech and Signal Processing
PublisherIEEE
PagesI25-I28
Number of pages4
Volume1
ISBN (Print)0780384849
DOIs
Publication statusPublished - 2004
Externally publishedYes
Event2004 IEEE International Conference on Acoustics, Speech, and Signal Processing - Montreal, Canada
Duration: 17 May 200421 May 2004

Publication series

NameProceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISSN (Print)1520-6149

Conference

Conference2004 IEEE International Conference on Acoustics, Speech, and Signal Processing
Country/TerritoryCanada
CityMontreal
Period17/05/0421/05/04

Fingerprint

Dive into the research topics of 'Discriminative training for speaker identification based on maximum model distance algorithm'. Together they form a unique fingerprint.

Cite this