Discriminative transformation for sufficient adaptation in text-independent speaker verification

Authors:
Hao Yang;Yuan Dong;Xianyu Zhao;Jian Zhao;Haila Wang
Affiliations:
Beijing University of Posts and Telecommunications, Beijing;France Telecom Research & Development Center, Beijing;France Telecom Research & Development Center, Beijing;Beijing University of Posts and Telecommunications, Beijing;France Telecom Research & Development Center, Beijing
Venue:
ISCSLP'06 Proceedings of the 5th international conference on Chinese Spoken Language Processing
Year:
2006

Citing 1
Cited 1

Investigation of silicon auditory models and generalization of linear discriminant analysis for improved speech recognition

Investigation of silicon auditory models and generalization of linear discriminant analysis for improved speech recognition

Discussion on score normalization and language robustness in text-independent multi-language speaker verification

ICIC'07 Proceedings of the intelligent computing 3rd international conference on Advanced intelligent computing theories and applications

Quantified Score

Hi-index	0.00

Visualization

Abstract

In conventional Gaussian Mixture Model – Universal Background Model (GMM-UBM) text-independent speaker verification applications, the discriminability between speaker models and the universal background model (UBM) is crucial to system’s performance. In this paper, we present a method based on heteroscedastic linear discriminant analysis (HLDA) that can enhance the discriminability between speaker models and UBM. This technique aims to discriminate the individual Gaussian distributions of the feature space. After the discriminative transformation, the overlapped parts of Gaussian distributions can be reduced. As a result, some Gaussian components of a target speaker model can be adapted more sufficiently during Maximum a Posteriori (MAP) adaptation, and these components will have more discriminative capability over the UBM. Results are presented on NIST 2004 Speaker Recognition data corpora where it is shown that this method provides significant performance improvements over the baseline system.