Abstract

This study presents a prior work of developing a single chip solution for Text-to-Speech synthesizer for Tamil (Tamil-TTS) language. Though there are enormous works presented in the recent days to address TTS for their native languages, the motivation of this study is to develop a low-cost FPGA based solution for Tamil TTS synthesizer. This study uses the unique feature of Tamil language to eliminate the complexity involved in accessing a database of stored audio signals. It uses only the audio signals of consonants and vowels in the stored memory locations. The compound characters from the segmented input text are generated using a Direct Digital Synthesizer by operating at three different frequencies of phonetic interval units of Tamil. The proposed system is implemented in Cyclone IVE EP4CE115F29C7 FPGA device and the implementation results show that the proposed system outperforms the other similar methods in terms of memory utilization, text-to-speech time, area utilization and power dissipation. The accuracy of the system is examined with 25 native speakers and acceptable accuracy scale has been reached.

Keywords:

FPGA implementation , speech synthesis , Tamil-TTS , text-to-speech,

References

1. Aida-Zade, K.R., C. Ardil and A.M. Sharifova, 2010. The main principles of text-to-speech synthesis system. Int. J. Comput. Electr. Automat. Control Inform. Eng., 7(3): 234-240.
   
2. Bamini, P.K., 2003. FPGA-based implementation of concatenative speech synthesis algorithm. M.Sc. Thesis, University of South Florida.
   
3. Bellur, A., K.B. Narayan, K.R. Krishnan and H.A. Murthy, 2011. Prosody modeling for syllable-based concatenative speech synthesis of Hindi and Tamil. Proceeding of the National Conference on Communications (NCC). Bangalore, pp: 1-5.
   CrossRef    
4. Chazan, D., R. Hoory, Z. Kons, A. Sagi, S. Shechtman and A. Sorin, 2005. Small footprint concatenative text-to-speech synthesis system using complex spectral envelope modeling. Proceeding of the Interspeech. Lisbon, Portugal, pp: 2569-2572.
   
5. Ferreira, J.P., C. Chesi, H. Cho, D. Baldewijns, D. Braga et al., 2014. On mirandese language resources for text-to-speech. Proceeding of the 4th International Workshop on Spoken Language Technologies for Under-resourced Languages.
   
6. Jayasankar, T. and J.A. Vijayaselvi, 2014. FPGA-based implementation of text analyser and syllable preparation for concatenative speech synthesis of tamil language. Aust. J. Basic Appl. Sci., 8(10): 102-109.
   
7. Khalifa, O.O., Z.H. Ahmad, A.H.A. Hashim and T.S. Gunawan, 2008. SMaTalk: Standard malay text to speech talk system. Signal Process. Int. J., 2(5): 1-16.
   
8. Klatt, D.H., 1987. Review of text-to-speech conversion for english. J. Acoust. Soc. Am., 82(3): 737-793.
   CrossRef    PMid:2958525    
9. Phan, T.S., A.T. Dinh, T.T. Vu and C.M. Luong, 2014. An Improvement of Prosodic Characteristics in Vietnamese Text to Speech System. In: Huynh, V.N. et al. (Eds.), Knowledge and System Engineering. Advances in Intelligent Systems and Computing, Springer International Publishing Switzerland, 244: 99-111.
   CrossRef    
10. Rama, G.L.J., A.G. Ramakrishnan, R. Muralishankar and V. Venkatesh, 2001. Thirukkural-a text to speech synthesis system. Proceeding of the Tamil Internet, pp: 92-97.
    
11. Saraswathi, S. and R. Vishalaksh, 2010. Design of multilingual speech synthesis system. Int. J. Intell. Inform. Manage., 2: 58-64.
    CrossRef    
12. Sen, A. and K. Samudravijaya, 2002. Indian accent text-to-speech system for web browsing. Sadhana, 27(1): 113-126.
    CrossRef    
13. Shih, C. and R. Sproat, 1996. Issues in text-to-speech conversion for mandarin. Comput. Linguist. Chinese Lang. Process., 1(1): 37-86.
    
14. Sivaradje, G. and P. Dananjayan, 2004. VHDL implementation of text to speech converter for satellite radio receivers. Proceeding of the National Communication Conference (NCC, 2004). Bangalore, India.
    
15. Violaro, F. and O. Boeffard, 1998. A hybrid model for text-to-speech synthesis. IEEE T. Speech Audi. P., 6(5): 426-434.
    CrossRef    

Competing interests

The authors have no competing interests.

Open Access Policy

This article is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.

Copyright

The authors have no competing interests.