DocumentCode
1874122
Title
Automatic speaker recognition using dynamic Bayesian network
Author
Sang, Lifeng ; Wu, Zhaohui ; Yang, Yingchun ; Zhang, Wanfeng
Author_Institution
Dept. of Comput. Sci. & Technol., Zhejiang Univ., Hangzhou, China
Volume
3
fYear
2003
fDate
6-9 July 2003
Abstract
This paper presents a novel approach to automatic speaker recognition using dynamic Bayesian network (DBN). DBNs have a precise and well-understand probabilistic semantics, and it has the ability to incorporate prior knowledge, to represent arbitrary non-linearities, and to handle hidden variables and missing data in a principled way with high extensibility. Experimental evaluation over YOHO corpus shows promising results compared to other classical methods.
Keywords
belief networks; probability; speaker recognition; arbitrary nonlinearity; automatic speaker recognition; dynamic Bayesian network; hidden variable; missing data; probabilistic semantics; Bayesian methods; Computer science; Heuristic algorithms; Hidden Markov models; Knowledge representation; Probability; Signal processing algorithms; Speaker recognition; Speech recognition; Vector quantization;
fLanguage
English
Publisher
ieee
Conference_Titel
Multimedia and Expo, 2003. ICME '03. Proceedings. 2003 International Conference on
Print_ISBN
0-7803-7965-9
Type
conf
DOI
10.1109/ICME.2003.1221386
Filename
1221386
Link To Document