Get all the updates for this publication
This paper presents robust feature extraction techniques, called Mel Power Karhunen Loeve Transform Coefficients (MPKC), Mel Power Coefficients (MPC) for an isolated digit recognition. This hybrid method involves Stevens’ Power Law of Hearing and Karhunen Loeve(KL) Transform to improve noise robustness. We have evaluated the proposed methods on a Hidden Markov Model (HMM) based isolated digit recognition system with TIDIGITS data for clean speech and also with noisy speech data. An increase in the recognition accuracy rate is observed with the proposed methods compared to conventional Mel Frequency Cepstral Coefficients (MFCC) technique. © 2005 - 2014 JATIT & LLS. All rights reserved.
Journal | Journal of Theoretical and Applied Information Technology |
---|---|
Publisher | Little Lion Scientific |
ISSN | 19928645 |