Abstract
Dynamic Time Warping (DTW) is template based cost minimization technique. We propose Hidden Markov Model (HMM) based enhanced DTW technique to efficiently recognize various speaking rate signals and for recognizing closely similar utterances. We extend the derivation of Viterbi and forward algorithms for finding optimized path alignment in new propose technique and extend the Baum-Welch algorithm to optimize the model parameters. The proposed technique is compared with conventional DTW technique, and from comparative results analysis we find that it improves the results from 84% to 94 % using DTW technique for Hindi spoken words for various speech utterances in different environmental conditions or for varying speakers.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Kumar, K., Agarwal, R.K.: Hindi speech recognition system using HTK. International Journal of Computing and Business Research 2(2) (May 2011) ISSN (Online): 2229-6166
Aggarwal, R.K., Dave, M.: Design and Modeling of A Speech Understanding System for Hindi Language, Deptt. of Computer Engg. N.I.T., Kurukshetra
Ranjan, S.: A Discrete Wavelet Transform Based Approach to Hindi Speech Recognition. In: 2010 International Conference on Signal Acquisition and Processing (2010)
Abdulla, W.H., Chow, D., Sin, G.: Cross-words Reference Template for DTW-based Speech Recognition Systems. In: TENCON 2003. Conference on Convergent Technologies for Asia-Pacific Region, October 15-17, vol. 4, pp. 1576–1579 (2003)
The online encyclopedia of writing systems & languages, http://www.omniglot.com/index.html
Furui, S.: Cepstral analysis technique for automatic speaker verification. IEEE Trans. ASSP-29(2), 254–272 (1981)
Furui, S.: Speaker-independent isolated word recognition using dynamic features of spectrum. IEEE ASSP-34(1), 52–59 (1986)
ETSI ES 201 108, V1.1.3.: ETSI standard: speech processing, transmission and quality aspects (STQ); Distributed speech recognition; Front-end feature extraction algorithm; Compression algorithms; Sect. 4, pp. 8–12, (September 2003)
Pruthi, T., Saksena, S., Das, P.K.: Swaranjali: Isolated word recognition for Hindi language using VQ and HMM, Hughes Software Systems and IIT Guwahati (2000)
Sharma, K.K., Kapoor, P., Chakraborty, P., Nandi, G.C.: Dynamic Spectrum Derived MFCC and HFCC Parameters and Human Robot Speech Interaction. In: International Conference on Advances in Computer Engineering–ACE 2011 (2011)
Hocine Bourouba, E., Bedda, M., Djemili, R.: Isolated Words Recognition System Based on Hybrid Approach DTW/GHMM. Informatica 30, 373–384 (2006)
Yaniv, R., Burshtein, D.: An Enhanced Dynamic Time Warping Model for Improved Estimation of DTW Parameters. IEEE Transactions on Speech and Audio Processing 11(3) (May 2003)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Kumar, S.K., Kant, L.K., Shachi, S. (2013). HMM Based Enhanced Dynamic Time Warping Model for Efficient Hindi Language Speech Recognition System. In: Das, V.V., Chaba, Y. (eds) Mobile Communication and Power Engineering. AIM 2012. Communications in Computer and Information Science, vol 296. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-35864-7_28
Download citation
DOI: https://doi.org/10.1007/978-3-642-35864-7_28
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-35863-0
Online ISBN: 978-3-642-35864-7
eBook Packages: Computer ScienceComputer Science (R0)