DocumentCode
1415479
Title
Independent component analysis applied to feature extraction for robust automatic speech recognition
Author
Potamitis, L. ; Fakotakis, N. ; Kokkinakis, G.
Author_Institution
Dept. of Electr. & Comput. Eng., Patras Univ., Greece
Volume
36
Issue
23
fYear
2000
fDate
11/9/2000 12:00:00 AM
Firstpage
1977
Lastpage
1978
Abstract
The authors explore independent component analysis (ICA) as a statistical technique for deriving suitable data-driven representational bases for the projection of spectra and cepstra in the context of automatic speech recognition (ASR). Based on the close link between the independent mechanisms of speech variability and the concept of statistical independence, they derive a new feature transformation that effects consistent improvement in recognition performance
Keywords
feature extraction; speech recognition; statistical analysis; ICA; cepstra projection; data-driven representational bases; feature extraction; feature transformation; independent component analysis; recognition performance improvement; robust automatic speech recognition; spectra projection; speech variability; statistical technique;
fLanguage
English
Journal_Title
Electronics Letters
Publisher
iet
ISSN
0013-5194
Type
jour
DOI
10.1049/el:20001365
Filename
888693
Link To Document