Voice biometrics using linear Gaussian model. Issue 1 (1st March 2014)

• Record Type: Journal Article
• Authors: Yang, Hai; Xu, Yunfei; Huang, Houjun; Zhou, Ruohua; Yan, Yonghong
• Is Part Of: IET biometrics. Volume 3:Issue 1(2014)
• Page Start: 9
• Page End: 15
• Publication Date: 2014-03-01
• Subjects: belief networks -- biometrics (access control) -- expectation‐maximisation algorithm -- Gaussian processes -- speaker recognition; linear Gaussian model‐based framework -- voice biometrics -- discrete‐time linear dynamical systems -- probabilistic linear discriminant analysis -- two‐covariance model -- expectation‐maximisation algorithm -- Bayesian solution -- log‐likelihood ratio score -- NIST 2010 speaker recognition evaluation -- normalised decision cost function; Biometric identification -- Periodicals; 570.15195
• DOI: 10.1049/iet-bmt.2013.0027
• Languages: English
• ISSNs: 2047-4938

Abstract

Abstract : This study introduces a linear Gaussian model‐based framework for voice biometrics. The model works with discrete‐time linear dynamical systems. The study motivation is to use the linear Gaussian modelling method in voice biometrics, and show that the accuracy offered by the linear Gaussian modelling method is comparable with other state‐of‐the‐art methods such as Probabilistic Linear Discriminant Analysis and two‐covariance model. An expectation–maximisation algorithm is derived to train the model and a Bayesian solution is used to calculate the log‐likelihood ratio score of all trials of speakers. This approach performed well on the core‐extended conditions of the NIST 2010 Speaker Recognition Evaluation, and is competitive compared with the Gaussian probabilistic linear discriminant analysis, in terms of normalised decision cost function.