International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
|
Volume 180 - Issue 42 |
Published: May 2018 |
Authors: M. Babul Islam |
![]() |
M. Babul Islam . Noisy Speech Recognition by Mel-LPC based AR-HMM with Power and Time Derivative Parameters. International Journal of Computer Applications. 180, 42 (May 2018), 1-5. DOI=10.5120/ijca2018917149
@article{ 10.5120/ijca2018917149, author = { M. Babul Islam }, title = { Noisy Speech Recognition by Mel-LPC based AR-HMM with Power and Time Derivative Parameters }, journal = { International Journal of Computer Applications }, year = { 2018 }, volume = { 180 }, number = { 42 }, pages = { 1-5 }, doi = { 10.5120/ijca2018917149 }, publisher = { Foundation of Computer Science (FCS), NY, USA } }
%0 Journal Article %D 2018 %A M. Babul Islam %T Noisy Speech Recognition by Mel-LPC based AR-HMM with Power and Time Derivative Parameters%T %J International Journal of Computer Applications %V 180 %N 42 %P 1-5 %R 10.5120/ijca2018917149 %I Foundation of Computer Science (FCS), NY, USA
In this paper, AR-HMM on mel-scale with power and Mel-LPC based time derivative parameters has been presented for noisy speech recognition. The mel-scaled AR coefficients and melprediction coefficients for Mel-LPC have been calculated on the linear frequency scale from the speech signal without applying bilinear transformation. This has been done by using a first-order allpass filter instead of unit delay. In addition, Mel-Wiener filter has been applied to the system to improve the recognition accuracy in presence of additive noise. The proposed system is evaluated on Aurora 2 database, and the overall recognition accuracy has been found to be 80.02% on the average.