Home            Contact us            FAQs
    
      Journal Home      |      Aim & Scope     |     Author(s) Information      |      Editorial Board      |      MSP Download Statistics

     Research Journal of Information Technology

    Abstract
2012(Vol.4, Issue:1)
Article Information:

Parameter Compensation for Mel-LP based Noisy Speech Recognition

Md. Mahfuzur Rahman, Md. Robiul Hoque and M. Babul Islam
Corresponding Author:  M. Babul Islam 
Submitted: 2011 July, 13
Accepted: 2011 August, 30
Published: 2012 March, 10
Abstract:
This study deals with a noise robust distributed speech recognizer for real-world applications by deploying feature parameter compensation technique. To realize this objective, Mel-LP based speech analysis has been used in speech coding on the linear frequency scale by applying a first-order all-pass filter instead of a unit delay. To minimize the mismatch between training and test phases, Cepstral Mean Normalization (CMN) and Blind Equalization (BEQ) have been applied to enhance Mel-LP cepstral coefficients as an effort to reduce the effect of additive noise and channel distortion. The performance of the proposed system has been evaluated on Aurora-2 database which is a subset of TIDigits database contaminated by additive noises and channel effects. The baseline performance, that is, for Mel-LPC the average word accuracy for test set A has found to be 59.05%. By applying the CMN and BEQ with the Mel-LP cepstral coefficients, the performance has been improved to 68.02 and 65.65%, respectively.

Key words:  Aurora-2 database, BEQ, bilinear transformation, CMN, Mel-LPC, ,
Abstract PDF HTML
Cite this Reference:
Md. Mahfuzur Rahman, Md. Robiul Hoque and M. Babul Islam, . Parameter Compensation for Mel-LP based Noisy Speech Recognition. Research Journal of Information Technology , (1): 7-12.
ISSN (Online):  2041-3114
ISSN (Print):   2041-3106
Submit Manuscript
   Information
   Sales & Services
Home   |  Contact us   |  About us   |  Privacy Policy
Copyright © 2024. MAXWELL Scientific Publication Corp., All rights reserved