Robust clustering approach to fuzzy Gaussian mixture models for speaker identification

Dat Tran; Michael Wagner

Robust clustering approach to fuzzy Gaussian mixture models for speaker identification

Dat Tran, Michael Wagner

Information Systems

Research output: Contribution to conference (non-published works) › Paper

8 Citations (Scopus)

Abstract

The Gaussian mixture model (GMM) is a currently used method for speaker recognition. The fuzzy GMM (FGMM) proposed in our previous work is a fuzzy clustering-based modification of the GMM. Although both the FGMM and the GMM are capable of achieving high identification accuracy, they have a common disadvantage in the problem of sensitivity to outliers. This paper presents an improvement for the FGMM to handle this problem. Experimental results on 16 speakers using the TI46 database are also reported.

Original language	English
Pages	337-340
Number of pages	4
Publication status	Published - 1999
Event	Proceedings of the 1999 3rd International Conference on Knowledge-Based Intelligent Information Engineering Systems (KES '99) - Adelaide, Aust Duration: 31 Aug 1999 → 1 Sept 1999

Conference

Conference	Proceedings of the 1999 3rd International Conference on Knowledge-Based Intelligent Information Engineering Systems (KES '99)
City	Adelaide, Aust
Period	31/08/99 → 1/09/99

Cite this

@conference{da982a2a8d944d268c3777d557c17398,

title = "Robust clustering approach to fuzzy Gaussian mixture models for speaker identification",

abstract = "The Gaussian mixture model (GMM) is a currently used method for speaker recognition. The fuzzy GMM (FGMM) proposed in our previous work is a fuzzy clustering-based modification of the GMM. Although both the FGMM and the GMM are capable of achieving high identification accuracy, they have a common disadvantage in the problem of sensitivity to outliers. This paper presents an improvement for the FGMM to handle this problem. Experimental results on 16 speakers using the TI46 database are also reported.",

author = "Dat Tran and Michael Wagner",

year = "1999",

language = "English",

pages = "337--340",

note = "Proceedings of the 1999 3rd International Conference on Knowledge-Based Intelligent Information Engineering Systems (KES '99) ; Conference date: 31-08-1999 Through 01-09-1999",

}

TY - CONF

T1 - Robust clustering approach to fuzzy Gaussian mixture models for speaker identification

AU - Tran, Dat

AU - Wagner, Michael

PY - 1999

Y1 - 1999

N2 - The Gaussian mixture model (GMM) is a currently used method for speaker recognition. The fuzzy GMM (FGMM) proposed in our previous work is a fuzzy clustering-based modification of the GMM. Although both the FGMM and the GMM are capable of achieving high identification accuracy, they have a common disadvantage in the problem of sensitivity to outliers. This paper presents an improvement for the FGMM to handle this problem. Experimental results on 16 speakers using the TI46 database are also reported.

AB - The Gaussian mixture model (GMM) is a currently used method for speaker recognition. The fuzzy GMM (FGMM) proposed in our previous work is a fuzzy clustering-based modification of the GMM. Although both the FGMM and the GMM are capable of achieving high identification accuracy, they have a common disadvantage in the problem of sensitivity to outliers. This paper presents an improvement for the FGMM to handle this problem. Experimental results on 16 speakers using the TI46 database are also reported.

UR - http://www.scopus.com/inward/record.url?scp=0033324475&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0033324475

SP - 337

EP - 340

T2 - Proceedings of the 1999 3rd International Conference on Knowledge-Based Intelligent Information Engineering Systems (KES '99)

Y2 - 31 August 1999 through 1 September 1999

ER -

Robust clustering approach to fuzzy Gaussian mixture models for speaker identification

Abstract

Conference

Other files and links

Fingerprint

Cite this