Title :
Discriminative temporal feature extraction for robust speech recognition
Author_Institution :
Inst. of Inf. Sci., Acad. Sinica, Taipei, Taiwan
fDate :
9/11/1997 12:00:00 AM
Abstract :
A discriminative temporal feature processing method for robust speech recognition is presented by combining the knowledge and the statistical methods. The cepstral features are first filtered by a RASTA method based on human hearing perception and then processed using the minimum classification error algorithm. Improved recognition performance can be achieved in both quiet and noisy environments
Keywords :
cepstral analysis; feature extraction; hearing; pattern classification; speech recognition; RASTA method; cepstral features; discriminative temporal feature extraction; human hearing perception; minimum classification error; noisy environments; recognition performance; robust speech recognition; statistical methods;
Journal_Title :
Electronics Letters
DOI :
10.1049/el:19971079
