This paper presents a Bangla (widely used as Bengali) automatic speech recognition system (ASR) by suppressing gender effects. Gender characteristic plays an important role on the performance of ASR. If there is a suppression process that represses the decrease of differences in acoustic-likelihood among categories resulted from gender factors, a robust ASR system can be realized. In the proposed method, we have designed a new ASR incorporating the Local Features (LFs) instead of standard mel frequency cepstral coefficients (MFCCs) as an acoustic feature for Bangla by suppressing the gender effects, which embeds three HMM-based classifiers for corresponding male, female and geneder-independent (GI) characteristics. In the experiments on Bangla speech database prepared by us, the proposed system has achieved a significant improvement of word correct rates (WCRs), word accuracies (WAs) and sentence correct rates (SCRs) in comparison with the method that incorporates Standard MFCCs.
%0 Journal Article
%1 IJACSA.2012.031115
%A B.K.M Mizanur Rahman Bulbul Ahamed, Md. Asfak-Ur-Rahman Khaled Mahmud Mohammad Nurul Huda
%D 2012
%J International Journal of Advanced Computer Science and Applications(IJACSA)
%K Acoustic AutomaticSpeech Effects Gender Hidden Markov Model. Model; Recognition; Suppression;
%N 11
%T Gender Effect Canonicalization for Bangla ASR
%U http://ijacsa.thesai.org/
%V 3
%X This paper presents a Bangla (widely used as Bengali) automatic speech recognition system (ASR) by suppressing gender effects. Gender characteristic plays an important role on the performance of ASR. If there is a suppression process that represses the decrease of differences in acoustic-likelihood among categories resulted from gender factors, a robust ASR system can be realized. In the proposed method, we have designed a new ASR incorporating the Local Features (LFs) instead of standard mel frequency cepstral coefficients (MFCCs) as an acoustic feature for Bangla by suppressing the gender effects, which embeds three HMM-based classifiers for corresponding male, female and geneder-independent (GI) characteristics. In the experiments on Bangla speech database prepared by us, the proposed system has achieved a significant improvement of word correct rates (WCRs), word accuracies (WAs) and sentence correct rates (SCRs) in comparison with the method that incorporates Standard MFCCs.
@article{IJACSA.2012.031115,
abstract = {This paper presents a Bangla (widely used as Bengali) automatic speech recognition system (ASR) by suppressing gender effects. Gender characteristic plays an important role on the performance of ASR. If there is a suppression process that represses the decrease of differences in acoustic-likelihood among categories resulted from gender factors, a robust ASR system can be realized. In the proposed method, we have designed a new ASR incorporating the Local Features (LFs) instead of standard mel frequency cepstral coefficients (MFCCs) as an acoustic feature for Bangla by suppressing the gender effects, which embeds three HMM-based classifiers for corresponding male, female and geneder-independent (GI) characteristics. In the experiments on Bangla speech database prepared by us, the proposed system has achieved a significant improvement of word correct rates (WCRs), word accuracies (WAs) and sentence correct rates (SCRs) in comparison with the method that incorporates Standard MFCCs.},
added-at = {2014-02-21T08:00:08.000+0100},
author = {{B.K.M Mizanur Rahman Bulbul Ahamed}, Md. Asfak-Ur-Rahman Khaled Mahmud Mohammad Nurul Huda},
biburl = {https://www.bibsonomy.org/bibtex/2f0d4f03be9f33a63266aab110131ed14/thesaiorg},
interhash = {74892019d75b36ca2e6adf3f4e7330e8},
intrahash = {f0d4f03be9f33a63266aab110131ed14},
journal = {International Journal of Advanced Computer Science and Applications(IJACSA)},
keywords = {Acoustic AutomaticSpeech Effects Gender Hidden Markov Model. Model; Recognition; Suppression;},
number = 11,
timestamp = {2014-02-21T08:00:08.000+0100},
title = {{Gender Effect Canonicalization for Bangla ASR}},
url = {http://ijacsa.thesai.org/},
volume = 3,
year = 2012
}