Technical Program

Paper Detail

Paper:	SLP-P14.6
Session:	Speaker Recognition: Models and Methods
Time:	Thursday, May 18, 14:00 - 16:00
Presentation:	Poster
Topic:	Speech and Spoken Language Processing: Speaker Verification
Title:	Multigrained Model Adaptation with MAP and Reference Speaker Weighting for Text Independent Speaker Verification
Authors:	Xianyu Zhao, Yuan Dong, France Telecom R&D Center (Beijing), China; Jun Luo, Tsinghua University, China; Hao Yang, Beijing University of Posts and Telecommunications, China; Haila Wang, France Telecom R&D Center (Beijing), China
Abstract:	When traditional Maximum a Posteriori (MAP) adaptation is used to adapt a universal background model (UBM), some model components with little or no enrollment data would remain unchanged in the derived speaker model. These model components would have weak discriminative capability over the background model, and would impair subsequent verification performance. In this paper, we present a new speaker adaptation method which combines MAP and Reference Speaker Weighting (RSW) adaptation in a hierarchical, multigrained mode. It enables all model components to be updated in a way that strikes a good balance between model complexity and available data. The experimental results of NIST speaker recognition evaluation confirmed the effective performance increase with this new method compared with using MAP or RSW adaptation techniques alone.