By Topic

Alleviating the small sample-size problem in i-vector based speaker verification

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

2 Author(s)
Wei Rao ; Dept. of Electron. & Inf. Eng., Hong Kong Polytech. Univ., Hong Kong, China ; Man-Wai Mak

This paper investigates the small sample-size problem in i-vector based speaker verification systems. The idea of i-vectors is to represent the characteristics of speakers in the factors of a factor analyzer. Because the factor loading matrix defines the possible speaker and channel-variability of i-vectors, it is important to suppress the unwanted channel variability. Linear discriminant analysis (LDA), within-class covariance normalization (WCCN), and probabilistic LDA are commonly used for such purpose. These methods, however, require training data comprising many speakers each providing sufficient recording sessions for good performance. Performance will suffer when the number of speakers and/or number of sessions per speaker are too small. This paper compares four approaches to addressing this small sample-size problem: (1) preprocessing the i-vectors by PCA before applying LDA (PCA+LDA), (2) replacing the matrix inverse in LDA by pseudo-inverse, (3) applying multi-way LDA by exploiting the microphone and speaker labels of the training data, and (4) increasing the matrix rank in LDA by generating more i-vectors using utterance partitioning. Results based on NIST 2010 SRE suggests that utterance partitioning performs the best, followed by multi-way LDA and PCA+LDA.

Published in:

Chinese Spoken Language Processing (ISCSLP), 2012 8th International Symposium on

Date of Conference:

5-8 Dec. 2012