By Topic

Robust speech recognition using adaptive noise threshold estimation and wavelet shrinkage

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

3 Author(s)
Tuan Van Pham ; Signal Process. & Speech Commun. Lab., Graz Univ. of Technol., Graz ; Kubin, G. ; Rank, E.

We propose an improved noise reduction method for robust speech recognition based on a perceptually statistical wavelet filtering algorithm. Perceptual noise thresholds are estimated from the universal thresholds for each critical wavelet subband. Fast changes of background noise are tracked adaptively by improving our statistical percentile filtering method. Smoothed wavelet shrinkage is applied to enhance noisy wavelet coefficients. Performance of the proposed denoising algorithm is evaluated in terms of recognition performance under adverse noisy conditions such as car and factory environments. Furthermore, it is compared to recent speech enhancement methods embedded in different state-of-the-art speech recognizers. Overall results indicate that almost similar recognition performance is obtained on the AURORA3 SPEECHDAT-Car corpus as compared to the HTK recognizer using the advanced front-end while there is an improvement when testing with the Loquendo recognizer on the SNOW-Factory corpus.

Published in:

Communications and Electronics, 2008. ICCE 2008. Second International Conference on

Date of Conference:

4-6 June 2008