Speaker verification using adapted Gaussian mixture models

被引：2852

作者：

Reynolds, DA ^{[1
]}

Quatieri, TF ^{[1
]}

Dunn, RB ^{[1
]}

机构：

[1] MIT, Lincoln Lab, Speech Syst Technol Grp, Lexington, MA 02420 USA

来源：

DIGITAL SIGNAL PROCESSING | 2000年 / 10卷 / 1-3期

关键词：

speaker recognition; Gaussian mixture models; likelihood ratio detector; universal background model; handset normalization; NIST evaluation;

D O I：

10.1006/dspr.1999.0361

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

In this paper we describe the major elements of MIT Lincoln Laboratory's Gaussian mixture model (GMM)-based speaker verification system used successfully in several NIST Speaker Recognition Evaluations (SREs). The system is built around the likelihood ratio test for verification, using simple but effective GMMs for likelihood functions, a universal background model (UBM) for alternative speaker representation, and a form of Bayesian adaptation to derive speaker models from the UBM. The development and use of a handset detector and score normalization to greatly improve verification performance is also described and discussed. Finally representative performance benchmarks and system behavior experiments on NIST SRE corpora are presented. (C) 2000 Academic Press.

引用

下载

页码：19 / 41

页数：23

共 50 条

[1] Speaker Verification Using Adapted Bounded Gaussian Mixture Model
Azam, Muhammad
Bouguila, Nizar
2018 IEEE INTERNATIONAL CONFERENCE ON INFORMATION REUSE AND INTEGRATION (IRI), 2018, : 300 - 307
[2] Optimization of speaker verification using adapted gaussian mixture models for high quality databases
Kandovan, Ramin Shaghaghi
Lashkari, Mohammad Reza Karim
Etemad, Yashar
PROCEEDINGS OF THE FOURTH IASTED INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING, PATTERN RECOGNITION, AND APPLICATIONS, 2007, : 264 - +
[3] SPEAKER IDENTIFICATION AND VERIFICATION USING GAUSSIAN MIXTURE SPEAKER MODELS
REYNOLDS, DA
SPEECH COMMUNICATION, 1995, 17 (1-2) : 91 - 108
[4] Efficient speaker change detection using adapted Gaussian mixture models
Malegaonkar, Amit S.
Ariyaeeinia, Aladdin M.
Sivakumaran, Perasiriyan
IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2007, 15 (06): : 1859 - 1869
[5] Effects of Feature Domain Normalizations on Text Independent Speaker Verification Using Sorted Adapted Gaussian Mixture Models
Saeidi, Rahim
Mohammadi, Hamid Reza Sadegh
Ganchev, Todor
Rodman, Robert D.
ADVANCES IN COMPUTER SCIENCE AND ENGINEERING, 2008, 6 : 493 - +
[6] Speaker verification using text-constrained Gaussian mixture models
Sturim, DE
Reynolds, DA
Dunn, RB
Quatieri, TF
2002 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS I-IV, PROCEEDINGS, 2002, : 677 - 680
[7] Forensic Speaker Verification Using Formant Features and Gaussian Mixture Models
Becker, Timo
Jessen, Michael
Grigoras, Catalin
INTERSPEECH 2008: 9TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2008, VOLS 1-5, 2008, : 1505 - +
[8] Speaker verification based on adapted Gaussian mixture model feature mapping
Department of Electronic Science and Technology, University of Science and Technology of China, Hefei 230027, China
Moshi Shibie yu Rengong Zhineng, 2009, 3 (417-421):
[9] Speaker Verification Using Gaussian Mixture Model
Jagtap, Shilpa S.
Bhalke, D. G.
2015 INTERNATIONAL CONFERENCE ON PERVASIVE COMPUTING (ICPC), 2015,
[10] Privacy-Preserving Speaker Verification and Identification Using Gaussian Mixture Models
Pathak, Manas A.
Raj, Bhiksha
IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2013, 21 (02): : 397 - 406

← 1 2 3 4 5 →