Advances in SVM-Based System Using GMM Super Vectors for Text-Independent Speaker Verification

• Published in: Tsinghua science and technology Vol. 13; no. 4; pp. 522 - 527
• Main Authors: Zhao, Jian, Dong, Yuan, Zhao, Xianyu, Yang, Hao, Lu, Liang, Wang, Haila
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.08.2008; School of Information Engineering,Beijing University of Posts and Telecommunications,Beijing 100876,China%France Telecom Research and Development Center,Beijing 100080,China
• Subjects: Gaussian mixture model super vector; NIST 06 speaker recognition evaluation; nuisance attribute projection; speaker verification; support vector machines; test normalization; Gaussian mixture model super vector; speaker verification; nuisance attribute projection; support vector machines; NIST 06 speaker recognition evaluation; test normalization
• ISSN: 1007-0214; 1878-7606; 1007-0214
• DOI: 10.1016/S1007-0214(08)70083-X

For text-independent speaker verification, the Gaussian mixture model (GMM) using a universal background model strategy and the GMM using support vector machines are the two most commonly used methodologies. Recently, a new SVM-based speaker verification method using GMM super vectors has been proposed. This paper describes the construction of a new speaker verification system and investigates the use of nuisance attribute projection and test normalization to further enhance performance. Experiments were conducted on the core test of the 2006 NIST speaker recognition evaluation corpus. The experimental results indicate that an SVM-based speaker verification system using GMM super vectors can achieve appealing performance. With the use of nuisance attribute projection and test normalization, the system performance can be significantly improved, with improvements in the equal error rate from 7.78% to 4.92% and detection cost function from 0.0376 to 0.0251.