Speaker clustering based on utterance-oriented Dirichlet process mixture model

Naohiro Tawara; Shinji Watanabe; Tetsuji Ogawa; Tetsunori Kobayashi

Speaker clustering based on utterance-oriented Dirichlet process mixture model

Naohiro Tawara^*, Shinji Watanabe, Tetsuji Ogawa, Tetsunori Kobayashi

^*Corresponding author for this work

School of Fundamental Science and Engineering

Research output: Contribution to journal › Conference article › peer-review

1 Citation (Scopus)

Abstract

This paper provides the analytical solution and algorithm of UO-DPMM based on a non-parametric Bayesian manner, and thus realizes fully Bayesian speaker clustering. We carried out preliminary speaker clustering experiments by using a TIMIT database to compare the proposed method with the conventional Bayesian Information Criterion (BIC) based method, which is an approximate Bayesian approach. The results showed that the proposed method outperformed the conventional one in terms of both computational cost and robustness to changes in tuning parameters.

Original language	English
Pages (from-to)	2905-2908
Number of pages	4
Journal	Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Publication status	Published - 2011 Dec 1
Event	12th Annual Conference of the International Speech Communication Association, INTERSPEECH 2011 - Florence, Italy Duration: 2011 Aug 27 → 2011 Aug 31

Keywords

Gibbs sampling
Non-parametric Bayesian model
Speaker clustering
Utterance-oriented DPMM

ASJC Scopus subject areas

Language and Linguistics
Human-Computer Interaction
Signal Processing
Software
Modelling and Simulation

Cite this

@article{f1eeba71b039453b9209e162d734695b,

title = "Speaker clustering based on utterance-oriented Dirichlet process mixture model",

abstract = "This paper provides the analytical solution and algorithm of UO-DPMM based on a non-parametric Bayesian manner, and thus realizes fully Bayesian speaker clustering. We carried out preliminary speaker clustering experiments by using a TIMIT database to compare the proposed method with the conventional Bayesian Information Criterion (BIC) based method, which is an approximate Bayesian approach. The results showed that the proposed method outperformed the conventional one in terms of both computational cost and robustness to changes in tuning parameters.",

keywords = "Gibbs sampling, Non-parametric Bayesian model, Speaker clustering, Utterance-oriented DPMM",

author = "Naohiro Tawara and Shinji Watanabe and Tetsuji Ogawa and Tetsunori Kobayashi",

year = "2011",

month = dec,

day = "1",

language = "English",

pages = "2905--2908",

journal = "Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH",

issn = "2308-457X",

note = "12th Annual Conference of the International Speech Communication Association, INTERSPEECH 2011 ; Conference date: 27-08-2011 Through 31-08-2011",

}

TY - JOUR

T1 - Speaker clustering based on utterance-oriented Dirichlet process mixture model

AU - Tawara, Naohiro

AU - Watanabe, Shinji

AU - Ogawa, Tetsuji

AU - Kobayashi, Tetsunori

PY - 2011/12/1

Y1 - 2011/12/1

N2 - This paper provides the analytical solution and algorithm of UO-DPMM based on a non-parametric Bayesian manner, and thus realizes fully Bayesian speaker clustering. We carried out preliminary speaker clustering experiments by using a TIMIT database to compare the proposed method with the conventional Bayesian Information Criterion (BIC) based method, which is an approximate Bayesian approach. The results showed that the proposed method outperformed the conventional one in terms of both computational cost and robustness to changes in tuning parameters.

AB - This paper provides the analytical solution and algorithm of UO-DPMM based on a non-parametric Bayesian manner, and thus realizes fully Bayesian speaker clustering. We carried out preliminary speaker clustering experiments by using a TIMIT database to compare the proposed method with the conventional Bayesian Information Criterion (BIC) based method, which is an approximate Bayesian approach. The results showed that the proposed method outperformed the conventional one in terms of both computational cost and robustness to changes in tuning parameters.

KW - Gibbs sampling

KW - Non-parametric Bayesian model

KW - Speaker clustering

KW - Utterance-oriented DPMM

UR - http://www.scopus.com/inward/record.url?scp=84865792512&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84865792512&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:84865792512

SN - 2308-457X

SP - 2905

EP - 2908

JO - Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

JF - Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

T2 - 12th Annual Conference of the International Speech Communication Association, INTERSPEECH 2011

Y2 - 27 August 2011 through 31 August 2011

ER -

Speaker clustering based on utterance-oriented Dirichlet process mixture model

Abstract

Keywords

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this