By Topic

Isolated word recognition using polynomial classifier

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
$31 $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

2 Author(s)
Nehe, N.S. ; S.G.G.S. Inst. of Eng. & Technol., Nanded, India ; Holambe, R.S.

This paper presents an isolated word recognition using polynomial classifier. Along with the high accuracy, speech recognition applications also required the low complexity and less storage space, which is achieved using the polynomial classifier. Speech features used are the well-known mel-frequency cepstral coefficient (MFCC). The performance of the said classifier is tested for MFCC of size 12 to 22 and the best one is selected for the further analysis. The effect of % overlap between the two frames is also evaluated. We also provide the performance comparison of polynomial classifier with the other classifiers like vector quantizer (VQ) and dynamic time warping (DTW). The recognition using polynomial classifier is found faster than the VQ and DTW and also requires less storage space, however it is found that the recognition rate using polynomial classifier is slightly less than the two.

Published in:

Control, Automation, Communication and Energy Conservation, 2009. INCACEC 2009. 2009 International Conference on

Date of Conference:

4-6 June 2009