Thumbnail
Access Restriction
Open

Author Shen, Wade ♦ Reynolds, Douglas
Source CiteSeerX
Content type Text
File Format PDF
Language English
Subject Domain (in DDC) Computer science, information & general works ♦ Data processing & computer science
Subject Keyword Discriminative Training ♦ Gmmbased Language Recognition ♦ Constrained Maximum Likelihood Linear Regression ♦ Speaker Variability ♦ Unsupervised Compensation ♦ Vocal Tract Length Normalization ♦ Decreased Test-time Computational Cost ♦ Nist Language Recognition Evaluation ♦ Mllr Transform ♦ State-of-the-art Accuracy ♦ Cmllr Adaption ♦ Gmm-based Language Recognition Performance ♦ Language Recognition Problem ♦ Feature-space Transform
Description In this paper we describe the application of a feature-space transform based on constrained maximum likelihood linear regression for unsupervised compensation of channel and speaker variability to the language recognition problem. We show that use of such transforms can improve baseline GMM-based language recognition performance on the 2005 NIST Language Recognition Evaluation (LRE05) task by 38%. Furthermore, gains from CMLLR are additive with other modeling enhancements such as vocal tract length normalization (VTLN). Further improvement is obtained using discriminative training, and it is shown that a system using only CMLLR adaption produces state-of-the-art accuracy with decreased test-time computational cost than systems using VTLN.
Educational Role Student ♦ Teacher
Age Range above 22 year
Educational Use Research
Education Level UG and PG ♦ Career/Technical Study
Learning Resource Type Article
Publisher Date 2008-01-01
Publisher Institution Proceeding of the IEEE International Conference on Acoustics, Speech and Signal Processing, Mar. 31-Apr. 4, IEEE Xplore Press, Las Vegas, NV