Title :
Research on Automatic Speaker Recognition Based on Speech Clustering
Author :
Xu, Limin ; Qian, Bo ; Cheng, Weiming ; Tang, Zhenmin
Author_Institution :
Dept. of Comput. Sci., Nanjing Univ. of Sci. & Technol.
fDate :
Aug. 30 2006-Sept. 1 2006
Abstract :
A novel approach of extracting speaker features based on speech clustering technology which employs both speaker´s personality and speech cues is proposed in this work for speaker recognition. Specifically, the speech clustering-based approach is first applied before speaker feature extraction and multi-feature which is extracted respectively from the distinct clusters based on speech clustering is combined as a speaker multi-feature. Those two information cues including speaker´s personality and speech are then effectively integrated using the multi-feature for achieving more robust results. The experiments show that using the template matching method the recognition rate with the multi-feature achieve 95.83%, which is 6.48% increase than the recognition accuracy with the long-term average feature. Moreover the average of false acceptance with the multi-feature decreased than the other ordinary features
Keywords :
feature extraction; pattern clustering; pattern matching; speaker recognition; speech processing; automatic speaker recognition; speaker feature extraction; speaker personality; speech clustering; speech clustering technology; speech cues; template matching method; Cepstral analysis; Computer science; Data mining; Feature extraction; Flowcharts; Speaker recognition; Speech analysis; Speech processing; Speech recognition; Vectors;
Conference_Titel :
Innovative Computing, Information and Control, 2006. ICICIC '06. First International Conference on
Conference_Location :
Beijing
Print_ISBN :
0-7695-2616-0
DOI :
10.1109/ICICIC.2006.340