Share Email Print

Proceedings Paper

Add prior knowledge to speaker recognition
Author(s): Dongdong Li; Yingchun Yang; Zhaohui Wu; Ting Huang
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Prior knowledge helps to make the speaker recognition system more reliable and robust. This paper presents a uniform framework of feature-level fusion to incorporate the prior knowledge for speaker recognition using gender information based on dynamic Bayesian network (DBN). DBNs are a new statistical approach, with the ability to handle hidden variables and missing data in a principled way with high extensibility. And thus, DBNs can describe the prior knowledge conveniently. Our contribution is to apply DBNs to construct a general feature-level fusion to combine the general acoustic feature like MFCC and prior information like gender into a single DBN for speaker identification. In our framework, gender information become additional observed data to influence both hidden variables and observed acoustic data. Experimental evaluation over a subnet of YOHO corpus show promising results.

Paper Details

Date Published: 28 March 2005
PDF: 9 pages
Proc. SPIE 5813, Multisensor, Multisource Information Fusion: Architectures, Algorithms, and Applications 2005, (28 March 2005); doi: 10.1117/12.603278
Show Author Affiliations
Dongdong Li, Zhejiang Univ. (China)
Yingchun Yang, Zhejiang Univ. (China)
Zhaohui Wu, Zhejiang Univ. (China)
Ting Huang, Zhejiang Univ. (China)

Published in SPIE Proceedings Vol. 5813:
Multisensor, Multisource Information Fusion: Architectures, Algorithms, and Applications 2005
Belur V. Dasarathy, Editor(s)

© SPIE. Terms of Use
Back to Top