Share Email Print

Proceedings Paper

Scale-transform-based features for application in speech recognition
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

We report recognition results using scale-transform based cepstral features in a telephone based digit recognition task. The method is based on the use of scale-transform based features for speaker-independent applications, which are insensitive to linear-frequency scaling effects and therefore reduce inter-speaker variability due to differences in vocal-tract lengths. We have implemented a digit recognition task using the proposed scale-transform based features and have compared the recognition accuracy obtained when compared to using mel-cepstrum based front-end features.

Paper Details

Date Published: 26 October 1999
PDF: 5 pages
Proc. SPIE 3813, Wavelet Applications in Signal and Image Processing VII, (26 October 1999); doi: 10.1117/12.366828
Show Author Affiliations
S. Umesh, Indian Institute of Technology (India)
Leon Cohen, CUNY/Hunter College (United States)
Douglas J. Nelson, U.S. Dept. of Defense (United States)

Published in SPIE Proceedings Vol. 3813:
Wavelet Applications in Signal and Image Processing VII
Michael A. Unser; Akram Aldroubi; Andrew F. Laine, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?