Abstract
This paper describes the improvement of the quality of Tamil text to speech using LPC based diphone database and the modification of syllable pitch through time scale modification. Speech is generated by concatenative speech synthesizer. Syllable units need to be concatenated such that spectral discontinuities are lowered at unit boundaries without degrading their quality. Smoothing is done by inserting suitable diphone at the concatenation boundary and changing the syllable pitch by performing time scale modification. The suitable diphone is chosen based on LPC coefficient files and their corresponding residuals.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Muralishankar, R., Ramakrishnan, A.G.: Robust Pitch detection using DCT based Spectral Autocorrelation. In: Conference on Multimedia Processing, Chennai, August 13-15, pp. 129–132 (2000)
Muralishankar, R., Ramakrishnan, A.G.: Human Touch to Tamil Speech Synthesizer. In: Tamilnet 2001, Kuala Lumpur, Malaysia, pp. 103–109 (2001)
Chowdhury, S., Datta, A.K., Chaudhuri, B.B.: Study of Intonation Patterns for text reading in standard colloquial Bengali. In: Proceedings of IWSMSP-2001 (2001)
Bandyopadhyay, A.: Some Important aspects of Bengali Speech Synthesis System, IEMCT JUNE,Tata McGraw-Hill (2002)
Sen, A.: Speech Synthesis in Indian Languages. In: Pre-Workshop Tutorial on Speech and Music Signal Processing IWSMSP-2001 (2001)
Ramakrishnan, G.: Issues in standardization for Text to Speech in Tamil. In: Tamilnet 2001, Kuala Lumpur, Malaysia (2001)
O’Shaughnessy, D.: Speech Communication - Human and Machine, 2nd edn. IEEE press, Los Alamitos (2000)
Jayavardhana Rama, G.L., Ramakrishnan, A.G., Vijay Venkatesh, V., Muralishankar, R.: Thirukkural: a text-to-speech synthesis system. In: Proc. Tamil Internet 2001, Kuala Lumpur, August 26-28, pp. 92–97 (2001)
Tang, M., Wang, C., Seneff, S.: Voice Transformations: From Speech Synthesis to Mamalian Vocalizations. In: Conference on Speech Communication and Technology, Denmark (2001)
Muralishankar, R., Ramakrishnan, A.G., Prathibha, P.: Dynamic Pitch changes for concatenative synthesis. In: SPPRA, Greece (2002)
Varho, S., Alku, P.: A Linear Predictive Method Using Extrapolated Samples for Modelling of Voiced Speech. In: Proceedings of IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, New Paltz, NY, Session IV, pp. 13–16 (1997)
Varho, S.: New Linear Predictive Methods for Digital Speech Processing (2001)
Garas, J., Sommen, P.C.W.: Time/Pitch Scaling Using The Constant-Q Phase Vocoder. Eindhoven University of Technology (1980)
Hunt, M., Zwierynski, D., Carr, R.: Issues in high quality {LPC} analysis and synthesis. In: Eurospeech 1989, Paris, France, vol. 2, pp. 348–351 (1989)
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
Krithiga, M.V., Geetha, T.V. (2004). Introducing Pitch Modification in Residual Excited LPC Based Tamil Text-to-Speech Synthesis. In: Manandhar, S., Austin, J., Desai, U., Oyanagi, Y., Talukder, A.K. (eds) Applied Computing. AACC 2004. Lecture Notes in Computer Science, vol 3285. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-30176-9_23
Download citation
DOI: https://doi.org/10.1007/978-3-540-30176-9_23
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-23659-7
Online ISBN: 978-3-540-30176-9
eBook Packages: Springer Book Archive