DocumentCode :
2922214
Title :
Speaker Identification in Unknown Noisy Conditions - A Universal Compensation Approach
Author :
Ming, Ji ; Stewart, Darryl ; Vaseghi, Saeed
Author_Institution :
Sch. of Comput. Sci., Queen´´s Univ., Belfast, UK
Volume :
1
fYear :
2005
fDate :
March 18-23, 2005
Firstpage :
617
Lastpage :
620
Keywords :
compensation; speaker recognition; arbitrary additive noise; background noise; clean speech training data; missing-feature method; multicondition training method; simulated noise data; speaker identification; spectral corruption; time-frequency component corruption; universal compensation; unknown noisy conditions; Additive noise; Background noise; Filtering; Noise reduction; Noise robustness; Speaker recognition; Speech enhancement; Speech recognition; Training data; Working environment noise;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Acoustics, Speech, and Signal Processing, 2005. Proceedings. (ICASSP '05). IEEE International Conference on
ISSN :
1520-6149
Print_ISBN :
0-7803-8874-7
Type :
conf
DOI :
10.1109/ICASSP.2005.1415189
Filename :
1415189
Link To Document :
https://search.ricest.ac.ir/dl/search/defaultta.aspx?DTC=49&DC=2922214
بازگشت