DocumentCode
3381547
Title
The statistical information formulation for noisy speech recognition
Author
Ming, Ji
Author_Institution
Dept. of Electr. Eng., Changsha Inst. of Technol., China
Volume
ii
fYear
1990
fDate
16-21 Jun 1990
Firstpage
237
Abstract
Approaches to noisy speech recognition are developed by considering the direct extraction of the phonetic information from the noisy speech measurement. The proposed approaches are based on a statistical representation of the noisy measurement information directly in terms of the phonetic information to be recognized. Recognition is done based on a maximum a posteriori formulation of the noisy speech recognition problem
Keywords
noise; speech recognition; statistical analysis; noisy speech recognition; phonetic information extraction; statistical information formulation; Data mining; Degradation; Gaussian noise; Information processing; Linear predictive coding; Noise measurement; Speech enhancement; Speech recognition; Timing; Training data;
fLanguage
English
Publisher
ieee
Conference_Titel
Pattern Recognition, 1990. Proceedings., 10th International Conference on
Conference_Location
Atlantic City, NJ
Print_ISBN
0-8186-2062-5
Type
conf
DOI
10.1109/ICPR.1990.119361
Filename
119361
Link To Document