A Bayesian Approach to Phoneme Detection for Uyghur

Abstract:

In this paper, we presented a semantic speech segmentation approach, in particular phoneme segmentation. In order to get phoneme level information, a novel voiced speech, unvoiced speech and silence (VUS) classification is proposed. Five parameters that can be extracted by short-time analysis methods are used to discriminate the phoneme boundary. Experiments on Uyghur broadcasting news indicate that the performance of proposed algorithm is satisfying.

• Periodical: Applied Mechanics and Materials (Volumes 303-306)
• Pages: 1030-1034
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.303-306.1030
• Online since: February 2013
• Authors: Muhetaer Shasike, Buheliqiguli Wasili, Xiao Li
• Keywords: Acoustic Feature, Keyword Spotting, Speech Recognition, Speech Segmentation, Unvoiced Speech, Voiced Speech

References

[1] Hamit A. Zakir: Introduction to Modern Uighur, Xinjiang University Press, China (2007).

[2] Lawrence R. Rabiner, Ronald W. Schafer: Theory and Speech Processing, Publishing House of Electronic Industry, China (2011).

[3] John R. Deller, Jr., John H. L. Hansen, John G. Proakis: Discrete-Time Processing of Speech Signals, IEEE Press, NY (2000).

[4] Thierry Dutoit, Ferran Marques: Applied Signal Processing A MATLAB-Based Proof of Concept, Springer, NY (2009).