ALIZE 3.0 - Open source toolkit for state-of-the-art speaker recognition

Anthony Larcher; Jean Francois Bonastre; Benoit Fauve; Kong Aik Lee; Christophe Lévy; Haizhou Li; John S.D. Mason; Jean Yves Parfait

ALIZE 3.0 - Open source toolkit for state-of-the-art speaker recognition

Anthony Larcher, Jean Francois Bonastre, Benoit Fauve, Kong Aik Lee, Christophe Lévy, Haizhou Li, John S.D. Mason, Jean Yves Parfait

Research output: Journal article publication › Conference article › Academic research › peer-review

89 Citations (Scopus)

Abstract

ALIZE is an open-source platform for speaker recognition. The ALIZE library implements a low-level statistical engine based on the well-known Gaussian mixture modelling. The toolkit includes a set of high level tools dedicated to speaker recognition based on the latest developments in speaker recognition such as Joint Factor Analysis, Support Vector Machine, i-vector modelling and Probabilistic Linear Discriminant Analysis. Since 2005, the performance of ALIZE has been demonstrated in series of Speaker Recognition Evaluations (SREs) conducted by NIST and has been used by many participants in the last NISTSRE 2012. This paper presents the latest version of the corpus and performance on the NIST-SRE 2010 extended task.

Original language	English
Pages (from-to)	2768-2772
Number of pages	5
Journal	Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Publication status	Published - Aug 2013
Externally published	Yes
Event	14th Annual Conference of the International Speech Communication Association, INTERSPEECH 2013 - Lyon, France Duration: 25 Aug 2013 → 29 Aug 2013

Keywords

I-vector
Open-source platform
Speaker recognition

ASJC Scopus subject areas

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

Cite this

@article{0a8ab37fedd64c5cb37bb11cda1fcb3e,

title = "ALIZE 3.0 - Open source toolkit for state-of-the-art speaker recognition",

abstract = "ALIZE is an open-source platform for speaker recognition. The ALIZE library implements a low-level statistical engine based on the well-known Gaussian mixture modelling. The toolkit includes a set of high level tools dedicated to speaker recognition based on the latest developments in speaker recognition such as Joint Factor Analysis, Support Vector Machine, i-vector modelling and Probabilistic Linear Discriminant Analysis. Since 2005, the performance of ALIZE has been demonstrated in series of Speaker Recognition Evaluations (SREs) conducted by NIST and has been used by many participants in the last NISTSRE 2012. This paper presents the latest version of the corpus and performance on the NIST-SRE 2010 extended task.",

keywords = "I-vector, Open-source platform, Speaker recognition",

author = "Anthony Larcher and Bonastre, {Jean Francois} and Benoit Fauve and Lee, {Kong Aik} and Christophe L{\'e}vy and Haizhou Li and Mason, {John S.D.} and Parfait, {Jean Yves}",

year = "2013",

month = aug,

language = "English",

pages = "2768--2772",

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

issn = "2308-457X",

note = "14th Annual Conference of the International Speech Communication Association, INTERSPEECH 2013 ; Conference date: 25-08-2013 Through 29-08-2013",

}

ALIZE 3.0 - Open source toolkit for state-of-the-art speaker recognition. / Larcher, Anthony; Bonastre, Jean Francois; Fauve, Benoit et al.
In: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, 08.2013, p. 2768-2772.

Research output: Journal article publication › Conference article › Academic research › peer-review

TY - JOUR

T1 - ALIZE 3.0 - Open source toolkit for state-of-the-art speaker recognition

AU - Larcher, Anthony

AU - Bonastre, Jean Francois

AU - Fauve, Benoit

AU - Lee, Kong Aik

AU - Lévy, Christophe

AU - Li, Haizhou

AU - Mason, John S.D.

AU - Parfait, Jean Yves

PY - 2013/8

Y1 - 2013/8

N2 - ALIZE is an open-source platform for speaker recognition. The ALIZE library implements a low-level statistical engine based on the well-known Gaussian mixture modelling. The toolkit includes a set of high level tools dedicated to speaker recognition based on the latest developments in speaker recognition such as Joint Factor Analysis, Support Vector Machine, i-vector modelling and Probabilistic Linear Discriminant Analysis. Since 2005, the performance of ALIZE has been demonstrated in series of Speaker Recognition Evaluations (SREs) conducted by NIST and has been used by many participants in the last NISTSRE 2012. This paper presents the latest version of the corpus and performance on the NIST-SRE 2010 extended task.

AB - ALIZE is an open-source platform for speaker recognition. The ALIZE library implements a low-level statistical engine based on the well-known Gaussian mixture modelling. The toolkit includes a set of high level tools dedicated to speaker recognition based on the latest developments in speaker recognition such as Joint Factor Analysis, Support Vector Machine, i-vector modelling and Probabilistic Linear Discriminant Analysis. Since 2005, the performance of ALIZE has been demonstrated in series of Speaker Recognition Evaluations (SREs) conducted by NIST and has been used by many participants in the last NISTSRE 2012. This paper presents the latest version of the corpus and performance on the NIST-SRE 2010 extended task.

KW - I-vector

KW - Open-source platform

KW - Speaker recognition

UR - http://www.scopus.com/inward/record.url?scp=84896111913&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:84896111913

SN - 2308-457X

SP - 2768

EP - 2772

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 - 14th Annual Conference of the International Speech Communication Association, INTERSPEECH 2013

Y2 - 25 August 2013 through 29 August 2013

ER -

ALIZE 3.0 - Open source toolkit for state-of-the-art speaker recognition

Abstract

Keywords

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this