DocumentCode :
2311253
Title :
Cohort-Based Speaker Model Synthesis for Channel Robust Speaker Recognition
Author :
Wu, Wei ; Zheng, Thomas Fang ; Xu, Mingxing
Author_Institution :
Dept. of Comput. Sci. & Technol., Tsinghua Univ., Beijing
Volume :
1
fYear :
2006
fDate :
14-19 May 2006
Abstract :
Speaker recognition over a public telephone network involves various types of transmission channels and handsets, which leads to mismatched channels (between the enrolled models and the test utterances), and hence to a significant decline in the speaker recognition performance. In this paper a cohort-based speaker model synthesis algorithm, which aims at synthesizing speaker models for channels where no enrollment data is available is proposed. This algorithm applies a priori knowledge of channels extracted from speaker-specific cohort sets to synthesize speaker models. Results for the China Criminal Police College (CCPC) speaker recognition corpus, which contains utterances from both a landline and a mobile channel, show significant improvements over the HT-norm and UBM-based speaker model synthesis algorithms
Keywords :
mobile radio; radiotelephony; speaker recognition; speech synthesis; voice communication; wireless channels; channel robust speaker recognition; cohort-based speaker model synthesis; mismatched channels; mobile channel; public telephone network; transmission channels; Intelligent networks; Intelligent systems; Laboratories; Network synthesis; Robustness; Speaker recognition; Speech recognition; Speech synthesis; Telephone sets; Testing;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Acoustics, Speech and Signal Processing, 2006. ICASSP 2006 Proceedings. 2006 IEEE International Conference on
Conference_Location :
Toulouse
ISSN :
1520-6149
Print_ISBN :
1-4244-0469-X
Type :
conf
DOI :
10.1109/ICASSP.2006.1660165
Filename :
1660165
Link To Document :
بازگشت