CFP last date
22 April 2024
Reseach Article

Speech Recognition using Energy and Zero Crossing Features with Kekre�s Proportionate Error Algorithm

Published on None 2011 by H.B.Kekre, A A Athawale, G J Sharma
journal_cover_thumbnail
International Conference and Workshop on Emerging Trends in Technology
Foundation of Computer Science USA
ICWET - Number 4
None 2011
Authors: H.B.Kekre, A A Athawale, G J Sharma
d107fa7c-d96b-4102-8774-55522b321c9a

H.B.Kekre, A A Athawale, G J Sharma . Speech Recognition using Energy and Zero Crossing Features with Kekre�s Proportionate Error Algorithm. International Conference and Workshop on Emerging Trends in Technology. ICWET, 4 (None 2011), 33-37.

@article{
author = { H.B.Kekre, A A Athawale, G J Sharma },
title = { Speech Recognition using Energy and Zero Crossing Features with Kekre�s Proportionate Error Algorithm },
journal = { International Conference and Workshop on Emerging Trends in Technology },
issue_date = { None 2011 },
volume = { ICWET },
number = { 4 },
month = { None },
year = { 2011 },
issn = 0975-8887,
pages = { 33-37 },
numpages = 5,
url = { /proceedings/icwet/number4/2095-algo487/ },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Proceeding Article
%1 International Conference and Workshop on Emerging Trends in Technology
%A H.B.Kekre
%A A A Athawale
%A G J Sharma
%T Speech Recognition using Energy and Zero Crossing Features with Kekre�s Proportionate Error Algorithm
%J International Conference and Workshop on Emerging Trends in Technology
%@ 0975-8887
%V ICWET
%N 4
%P 33-37
%D 2011
%I International Journal of Computer Applications
Abstract

This paper presents a novel method for isolated English word recognition based on energy and zero crossing features with vector quantization. This isolated word recognition method consists of two phases, feature extraction phase and recognition phase. In feature extraction, end points are detected and noise is removed using end point detection algorithm, a feature vector is obtained by combining the energy and zero cross rate into a different feature vector dimensions of 8, 10 and 12. Recognition phase consists of two steps, feature training and testing, in feature training, codebooks for each reference samples are generated using LBG and KPE Vector Quantization algorithm. For testing Euclidean distance is calculated between test sample feature vector and codebook of all reference speech samples. Speech sample with minimum average distance is selected. Experimental results showed that the maximum recognition rate of 82% is obtained for KPE with codebook size of 64.

References
  1. A. Gersho, R.M. Gray, “Vector Quantization and Signal Compression”, Kluwer Academic Publishers, Boston, MA, 1991.
  2. D. A. Reynolds, “Experimental evaluation of features for Robust speaker identification”, IEEE Trans. Speech Audio Process., vol. 2, no. 4, pp. 639–643, Oct. 1994.
  3. H. B. Kekre, Tanuja K. Sarode, “Speech Data Compression using Vector Quantization”, WASET International Journal of Computer and Information Science and Engineering (IJCISE), Fall 2008, Volume 2, Number 4, pp: 251-254, 2008.
  4. H.B.Kekre, Ms Vaishali Kulkarni,’Speaker Identification by using Vector Quantization’, International Journal of Engineering Science and Technology, Vol. 2(5), 2010, 1325-1331.
  5. H. B. Kekre, Tanuja K. Sarode, “Two-level Vector Quantization Method for Codebook Generation using Kekre’s Proportionate Error Algorithm”, International Journal of Image Processing, Volume - 4, Issue -1.
  6. H. B. Kekre, Tanuja K. Sarode, “New Clustering Algorithm for Vector Quantization using Rotation of Error Vector”, (IJCSIS) International Journal of Computer Science and Information Security,Volume-7,No-3,2010.
  7. H. B. Kekre, Vaishali Kulkarni, “Performance Comparison Of Speaker Recognition using Vector Quantization by LBG and KFCG”, International Journal of Computer Applications, vol. 3, July 2010.
  8. H. B. Kekre, Tanuja K. Sarode, “Fast Codebook Generation Algorithm for Color Images using Vector Quantization,” International Journal of Computer Science and Information Technology, Vol. 1, No. 1, pp: 7-12, Jan 2009.
  9. H. B. Kekre, Tanuja K. Sarode, “An Efficient Fast Algorithm to Generate Codebook for Vector Quantization,” First International Conference on Emerging Trends in Engineering and Technology, ICETET-2008, held at Raisoni College of Engineering, Nagpur, India, 16-18 July 2008, available at online IEEE Xplore.
  10. H B Kekre, Archana Athawale, Tanuja Sarode and Kalpana Sagvekar, “Increased Capacity of Information Hiding using Mixed Codebooks of Vector Quantization Algorithms: LBG, KPE and KMCG”, International Journal of Advances in Computational Sciences and Technology, Volume 3 Number 2 (2010) pp. 245–256.
  11. L.R. Rabiner and B.H. Juang, “Fundamentals of Speech Recognition”, Prentice-Hall, Englewood Cliffs, N.J.Prentice-Hall, 1993.
  12. Mohamed Debyeche, Jean-Paul Haton & Amrane Houacine, “Improved Vector Quantization Approach for Discrete HMM Speech Recognition System”, International Arab Journal of Information Technology – 2007.
  13. Navnath S. Nehe, Raghunath S. Holambe,” Isolated Word Recognition using Normalized Teager Energy Cepstral Features”, Proceedings IEEE , International Conference on Advances in Computing, Control, and Telecommunication Technologies,2009, pp. 106-110.
  14. Poonam Bansal, Amita Dev, Shail Bala Jain, “Optimum HMM Combined with Vector Quantization for Hindi Speech Word Recognition”, Proceedings of IETE Journal of Research, vol-54, issue-4, July-Aug-2008.
  15. Poonam Bansal, Amita Dev, Shail Bala Jain,”Enhanced Feature Vector Set For VQ Recoginizer In Isolated Word Recoginition”,Proceedings of International Conference Information Research & Applications, i.Tech-2007,Verna, Bulgeria , pp.390-395,June-2007.
  16. Rabiner, L. R. and Sambur, M. R., "An Algorithm for Determining the Endpoints of Isolated Utterances," The Bell System Technical Journal, Vol. 54, No. 2, February 1975.
  17. Shivesh Ranjan,’ A Discrete Wavelet Transform Based Approach to Hindi Speech Recognition’, Proceedings IEEE, International Conference on Signal Acquisition and Processing, 2010, pp. 345-348.
  18. Y. Linde, A. Buzo, and R. M. Gray, “An algorithm for vector quantizer design”, IEEE Trans. Commun.’ vol. COM-28, no. 1, pp. 84-95, 1980.
Index Terms

Computer Science
Information Sciences

Keywords

Isolated Speech Recognition Vector Quantization Code vector Codebook Euclidean Distance