CFP last date
22 April 2024
Reseach Article

Automatic Continuous Speech Segmentation to Improve Tamil Text-to-Speech Synthesis

by T.Jayasankar, Dr R.Thangarajan, Dr.J.Arputha Vijaya
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Volume 25 - Number 1
Year of Publication: 2011
Authors: T.Jayasankar, Dr R.Thangarajan, Dr.J.Arputha Vijaya
10.5120/2994-4023

T.Jayasankar, Dr R.Thangarajan, Dr.J.Arputha Vijaya . Automatic Continuous Speech Segmentation to Improve Tamil Text-to-Speech Synthesis. International Journal of Computer Applications. 25, 1 ( July 2011), 31-36. DOI=10.5120/2994-4023

@article{ 10.5120/2994-4023,
author = { T.Jayasankar, Dr R.Thangarajan, Dr.J.Arputha Vijaya },
title = { Automatic Continuous Speech Segmentation to Improve Tamil Text-to-Speech Synthesis },
journal = { International Journal of Computer Applications },
issue_date = { July 2011 },
volume = { 25 },
number = { 1 },
month = { July },
year = { 2011 },
issn = { 0975-8887 },
pages = { 31-36 },
numpages = {9},
url = { https://ijcaonline.org/archives/volume25/number1/2994-4023/ },
doi = { 10.5120/2994-4023 },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Journal Article
%1 2024-02-06T20:10:40.245768+05:30
%A T.Jayasankar
%A Dr R.Thangarajan
%A Dr.J.Arputha Vijaya
%T Automatic Continuous Speech Segmentation to Improve Tamil Text-to-Speech Synthesis
%J International Journal of Computer Applications
%@ 0975-8887
%V 25
%N 1
%P 31-36
%D 2011
%I Foundation of Computer Science (FCS), NY, USA
Abstract

Emerging growth of information and communication technologies has influenced the research trends to focus on speech technologies. This paper we have investigated the development of automatic Tamil speech segmentation system which would act as test bed as well as foundation for several speech applications involving Tamil language. This study proposes an algorithm for automatic segmentation of Tamil voiced speech. The calculations of absolute energy and zero crossing rates are used to process speech samples to accomplish the segmentation. The Algorithm are written and compiled using Matlab.

References
  1. R.Thangarajan, Natarajan A. M “Syllable Based Continuous Speech Recognition for Tamil”, in South Asian language review, VOLXVIII No 1, 2008
  2. Nageshwara Rao,S. Thomas, T. Nagarajan and Hema A. Murthy,”Text-to-speech synthesis using syllable like units, proceedings of National Conference on Communication (NCC) 2005, pp. 227-280, IIT.
  3. Samuel Thomas, M. Nageshwara Rao, Hema A. Murthy and C.S. Ramalingam, “Natural Sounding TTS based on Syllable-like Units”, proceedings of 14th European Signal Processing Conference, Florence, Italy, Sep2006.
  4. Jayasankar.T, Arputha Vijayaselvi .J “Realization of Tamil Syllables Text To Speech Transferring System using FPGA” in Tamil Internet 2010, Coimbatore.
  5. Venugopalakrishna.Y.R. et.al., “ Design and Development of a Text-To-Speech Synthesizer for Indian Languages”, pp. 259-262,proceedings of National Conference on Communication (NCC) 008,IIT-Bombay,February 2008.
  6. A.G.Ramakrishnan, “Thirukural text to speech synthesis system”, proco.Tamil Internet 2001, Kuala Lumpur.
  7. Rabiner, L.R. and Sambur, M.R., 1975.“An Algorithm for Determining the Endpoints of Isolated Utterances”, BellSjjsl. Tech. J., Vol. 54, pp.297-3 1 5.
  8. Rabiner, L.R.and Schafer, R.W., 1978 Digital Processing of Speech Signals, Prentice-Hall Inc.
Index Terms

Computer Science
Information Sciences

Keywords

Speech Segmentation Tamil Zero- crossing rate