Abstract
This paper presents a Thai syllable speech recognition system with the capability to achieve high accuracy of Thai syllable speech and Thai tone recognition. The recognition accuracy of 97.84% is achieved for Thai syllable speech recognition using the Continuous Density Hidden Markov Model (CDHMM). To provide a faster response, a beam pruning technique is applied, in which the result shows that by using this technique with an appropriate beam width, the recognition time can be reduced by more than 4 times. As Thai is tonal language, tone recognition is crucial for distinguishing meanings of Thai syllables. To obtain high rates of tone recognition in the Thai language, the CDHMM and a mixed acoustic feature method are employed. The tone recognition rates of 97.88%, 97.36%, 98.81%, 90.67% and 100.0% are achieved for mid, low, falling, high and rising tones, respectively.
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
Weerawat, T.: Speaker Dependent Voice Recognition of Thai Language, Master Thesis, Electrical Engineering, King Mongkut’s Institute of Technology Ladkrabang (1998)
Suwancheewasiri, C.: Thai Speech Recognition for Speaker-dependent 500-word Vocabulary Based on Phonemic Distinctive Features of Isolated Syllables and Neural Network. In: Proceedings of the Fifth National Computer Science and Engineering Conference, pp. 59–69 (2001)
Lyu, R.Y., et al.: Isolated Mandarin Base-syllable Recognition Based-upon the Segmental Probability Model. IEEE Trans on Speech and Audio Processing 6(3), 293–299 (1998)
Thanasanurak, W.: Thai Syllable Speech Recognition by Segmental Probability Model, Master’s Thesis, Department of Computer Science, Mahidol University (2001)
Tungthangthum, A.: Tone Recognition for Thai. IEEE Asia-Pacific Conference on Circuits Systems, pp. 157-160 (1998)
Rabiner, L.R., Juang, B.H.: Fundamentals of Speech Recognition. Prentice-Hall, Inc, Englewood Cliffs (1993)
Ortmanns, S., Eiden, A., Ney, H., Coenen, N.: Look-ahead Techniques for Fast Beam Search. In: ICASSP, vol. 3, pp. 1783–1786 (1997)
Yong, Q., Fu-Yuan, M., Chang-Li, L., Ding-Hua, G.: Chinese Speech Recognition System with Very Large Vocabulary. In: International Conference on Signal Processing, October 1996, vol. 1, pp. 817–820 (1996)
Xuedong, H., Alex, A., Hsiao-wuen, H.: Spoken Language Processing. Prentice-Hall, Inc, Englewood Cliffs (2001)
Lee, T., Chan, P.C., Chan, L.W., Cheng, Y.H., Mak, B.: Tone Recognition of Isolated Cantonese Syllables. IEEE Trans on Speech and Audio Processing 3(3), 204–209 (1995)
Xu, Y.: Effects of Tone and Focus on the Formation and Alignment of f0 Contours. Journal of Phonetics, 55–105 (1999)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Tangwongsan, S., Po-Aramsri, P., Phoophuangpairoj, R. (2004). Highly Efficient and Effective Techniques for Thai Syllable Speech Recognition. In: Maher, M.J. (eds) Advances in Computer Science - ASIAN 2004. Higher-Level Decision Making. ASIAN 2004. Lecture Notes in Computer Science, vol 3321. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-30502-6_19
Download citation
DOI: https://doi.org/10.1007/978-3-540-30502-6_19
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-24087-7
Online ISBN: 978-3-540-30502-6
eBook Packages: Computer ScienceComputer Science (R0)