CFP last date
20 December 2024
Call for Paper
January Edition
IJCA solicits high quality original research papers for the upcoming January edition of the journal. The last date of research paper submission is 20 December 2024

Submit your paper
Know more
The week's pick
Responsive image
Improved Shuffled Frog Leaping Algorithm with Self-Adaptive Shuffling for Fuzzy Logic PD+G Controller Optimization in Robotic Manipulators

Duc Hoang Nguyen
Random Articles
Reseach Article

Continuous Hindi Speech Recognition using Monophone based Acoustic Modeling

Published on March 2014 by Ankit Kumar, Mohit Dua, Tripti Choudhary
journal_cover_thumbnail

International Conference on Advances in Computer Engineering and Applications
Foundation of Computer Science USA
ICACEA - Number 1
March 2014
Authors: Ankit Kumar, Mohit Dua, Tripti Choudhary
0ba1365a-ddae-4b66-9727-7ebb8e22a18f

Ankit Kumar, Mohit Dua, Tripti Choudhary . Continuous Hindi Speech Recognition using Monophone based Acoustic Modeling. International Conference on Advances in Computer Engineering and Applications. ICACEA, 1 (March 2014), 15-19.

@article{
author = { Ankit Kumar, Mohit Dua, Tripti Choudhary },
title = { Continuous Hindi Speech Recognition using Monophone based Acoustic Modeling },
journal = { International Conference on Advances in Computer Engineering and Applications },
issue_date = { March 2014 },
volume = { ICACEA },
number = { 1 },
month = { March },
year = { 2014 },
issn = 0975-8887,
pages = { 15-19 },
numpages = 5,
url = { /proceedings/icacea/number1/15610-1426/ },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Proceeding Article
%1 International Conference on Advances in Computer Engineering and Applications
%A Ankit Kumar
%A Mohit Dua
%A Tripti Choudhary
%T Continuous Hindi Speech Recognition using Monophone based Acoustic Modeling
%J International Conference on Advances in Computer Engineering and Applications
%@ 0975-8887
%V ICACEA
%N 1
%P 15-19
%D 2014
%I International Journal of Computer Applications
Abstract

Speech is a natural way of communication and it provides an intuitive user interface to machines. Although the performance of automatic speech recognition (ASR) system is far from perfect. The overall performance of any speech recognition system is highly depends on the acoustic modeling. Hence generation of an accurate and robust acoustic model holds the key to satisfactory recognition performance. In this paper, we compare the performance of continuous Hindi speech recognition system with different vocabulary sizes and feature extraction techniques. Mel frequency cepstral coefficient (MFCC) and perceptual linear prediction (PLP) both are used as a feature extraction techniques in our proposed system. Monophone based acoustic modeling is done by Hidden Markov Model (HMM) at the back-end of an ASR system. HTK 3. 4. 1 toolkit is used for the implementation of this system. The system is trained for 70 different Hindi words. The experimental result shows that our system is able to achieve 95. 08% accuracy, when we use MFCC as a feature extraction technique.

References
  1. Aggarwal, R. K. and Dave, M. 2011. Using Gaussian mixture for Hindi speech recognition system, International Journal of Speech processing, image Processing and Pattern Recognition, vol. 4, no. 4.
  2. Aggarwal, R. K. and Dave, M. 2010. An Empirical Approach for Optimization of Acoustic models in Hindi Speech Recognition Systems, 8th International conference on Natural language processing, ICON-2010.
  3. Lee, C. H. , Gauvain, J. L. , Pieraccini, R. and Rabiner, L. R. 1993. Large vocabulary speech recognition using subword units, Speech Communication, vol. 13, pp. 263–279.
  4. Young, S. , Evermann, G. et al. 2009. The HTK book. Cambridge: Microsoft Corporation and Cambridge University Engineering Department.
  5. Pruthi, T. , Saksena, S. and Das, P. K. 2000. Swaranjali: Isolated Word Recognition for Hindi Language using VQ and HMM," Paper Presented at International Conference on Multimedia Processing and Systems (ICMPS), IIT Madras, India.
  6. Kumar, K. and Aggarwal, R. K. 2011. Hindi Speech Recognition System using HTK, International Journal of Computing and Business Research, vol. 2, issue 2.
  7. Mishra, A. N. et al. , 2012. Robust Features for Connected Hindi digits Recognition, Int. Journal of Signal Processing, Image Processing and pattern Recognition, Vol. 4, No. 2.
  8. Sinha, S, Agrawal, S. S. and Jain, A. 2013. Continuous density Hidden Morkov Model for context dependent Hindi speech recognition, Int. Conference on Advances in Computing, Communication and Informatics (ICACCI), pp. 1953-1958, IEEE.
  9. Aggarwal, R. K. and Dave, M. 2011. Using Gaussian mixture for Hindi Speech Recognition System, International Journal of Signal Processing, Image Processing and pattern Recognition, SERSC Korea, vol. 4, no. 4.
  10. Kumar, Gaurav et al. 2012. Development of Application Specific Continuous Speech Recognition System in Hindi, Journal of Signal and Information Processing, 3,394-401.
  11. Banerjee, Pratyush et al. 2008. Application of Triphone Clustring in Acoustic Modeling for Continuous Speech Recognition in Bengali, 19th international conference on Pattern Recognition, pp. 1-4, IEEE.
  12. Ghai, W. and Singh, N. 2013. Phone based acoustic modeling for automatic speech recognition for punjabi language, Journal of Speech Sciences, vol. 3, no. 1, pp 69-83.
  13. Aubert, X. L. 2002. An overview of decoding techniques for large vocabulary continuous speech recognition, Computer Speech and Language, vol. 16, no. 1, pp. 89–114.
  14. Becchetti, C. and Ricotti, L. P. Speech Recognition Theory and C++ Implementation, 3rd ed. , vol. 2, John Wiley & Sons, pp 121-141.
  15. Furui, Sadaoki 2005. 50 Years of progress in Speech and Speaker Recognition Research, ECTI Transaction on Computer and Information Technology, vol. 1, no. 2.
  16. Rudnicky, A. I. , Hauptmann, A. G. and Lee, K. 1994. Survey of Current Speech Technology, Communication of the ACM, vol. 37, no. 3.
  17. O'shaughnessy, D. 2013. Acoustic analysis for automatic speech recognition, proceeding of the IEEE, vol. 101, no. 5.
Index Terms

Computer Science
Information Sciences

Keywords

Hindi Speech Recognition Automatic Speech Recognition Hmm Mfcc