Type-2 fuzzy GMM-UBM for text-independent speaker verification

被引：4

作者：

Pinheiro, Hector N. B. ^{[1
]}

Ren, Tsang Ing ^{[1
,2
]}

Cavalcanti, George D. C. ^{[1
]}

Jyh, Tsang Ing ^{[3
]}

Sijbers, Jan ^{[2
]}

机构：

[1] Univ Fed Pernambuco UFPE, CIn, Recife, PE, Brazil

[2] Univ Antwerp, Dept Phys, iMinds Vis Lab, Antwerp, Belgium

[3] Alcatel Lucent, Bell Labs, Antwerp, Belgium

来源：

2013 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS (SMC 2013) | 2013年

关键词：

Speaker verification; GMM-UBM; adaptative GMM-UBM; type-2 fuzzy GMM; GAUSSIAN MIXTURE-MODELS; SETS;

D O I：

10.1109/SMC.2013.738

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

This paper proposes the use of a type-2 fuzzy framework in the standard GMM-UBM based text-independent speaker verification systems. Based on type-2 fuzzy sets, the framework provides pertinence intervals for the models. The decision process is obtained using a Support Vectors Machine (SVM) that processes the interval likelihoods. A Voice Activity Detection (VAD) algorithm was also used to discard the parts of the speech signal without voice. The proposed method was tested on the MIT Device Speaker Verification Corpus which contains several different mobile devices used in different environments. The result shows the robustness of the system and the improvements in the verification ratios of the T2F-GMM-UBM compared to the classical GMM-UBM based systems.

引用

页码：4328 / 4331

页数：4

共 13 条

[1]

[Anonymous], 1997, P EUR 97 RHOD GREEC

[2]

DOU HJ, 2010, SIGN PROC ICSP 2010, P502

[3]

Duda R. O., 1973, Pattern Classification and Scene Analysis, V3

[4] Maximum a Posteriori Estimation for Multivariate Gaussian Mixture Observations of Markov Chains [J].

Gauvain, Jean-Luc ;

Lee, Chin-Hui .

IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING, 1994, 2 (02) :291-298

[5] Type-2 fuzzy sets and systems: An overview [J].

Mendel, Jerry M. .

IEEE COMPUTATIONAL INTELLIGENCE MAGAZINE, 2007, 2 (01) :20-29

[6] Type-2 fuzzy sets made simple [J].

Mendel, JM ;

John, RI .

IEEE TRANSACTIONS ON FUZZY SYSTEMS, 2002, 10 (02) :117-127

[7] ROBUST TEXT-INDEPENDENT SPEAKER IDENTIFICATION USING GAUSSIAN MIXTURE SPEAKER MODELS [J].

REYNOLDS, DA ;

ROSE, RC .

IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING, 1995, 3 (01) :72-83

[8] Speaker verification using adapted Gaussian mixture models [J].

Reynolds, DA ;

Quatieri, TF ;

Dunn, RB .

DIGITAL SIGNAL PROCESSING, 2000, 10 (1-3) :19-41

[9]

REYNOLDS DA, 1997, P EUR, P963

[10]

Tsang I. R., 2012, INT C SYST MAN CYB I

← 1 2 →