A Text To Speech (TTS) synthesis is a computer based system that should be able to read any text aloud. Thus TTS technology is essential to those people who are visually impaired. It also plays a very important role in the field of Telecommunication, Industrial and educational applications. Thus TTS has been developed for foreign languages and is well established. As Indian language characters are complex in nature, it is not a straight forward approach to build the TTS system for Indian languages as compared to English. India is a country of multi languages among them Hindi is one of the 23 official language. Hence this paper discusses development of Hindi TTS system. Syllable units in Hindi language are better choice than any other units because each character in Hindi language is close to syllable which is in the form of CVC (C: consonant, V: vowel). Existing Hindi TTS can be done using phone and diphone. The disadvantage in the existing system is that it requires larger concatenation points and has low quality speech output. It is observed that the quality of the synthesized sentences can be improved by using polysyllable units. In the proposed system, the developed database consists of more than 25,000 bisyllable and 1,200 syllables considering 3 positions of syllable in a word i. e. start, middle and end. The obtained results were compared with monosyllable based TTS, it indicated that the naturalness and intelligible of speech output is high compared to monosyllable based TTS system.

1. Sanghamitra Mohanty,"Syllable based indian languagetext to speech system ", International Journal of Advances in Engineering & Technology,Vol. 1, ISSN: 2231-1963,May 2011.
2. D. J. Ravi, Sudarshan Patilkulkarni, "Evaluation of kannada text-to-speech [ktts] system", ISSN: 2277 128X, Volume 2, Issue 1, January 2012.
3. Kiruthiga S and Krishnamoorthy K, "Annotating Speech Corpus for Prosody Modeling in Indian Language Text to Speech Systems", IJCSI International Journal of Computer Science Issues, Vol. 9, Issue 1, No 1, January 2012.
4. S P Kishore and Alan W Black ,"Unit Size in Unit Selection Speech Synthesis ",1317- 1320 EUROSPEECH – GENEVA, pg 1317-1320, 2003.
5. Laba Kr Thakuria,Prof. P. H Talukadar "Text to speech synthesis of GALO and ADI languages using polysyllabic units", ,ISSN 2347-7393,2014.
6. D. Sasirekha, E. Chandra "Text to speech: a simple tutorial", ISSN: 2231-2307, Volume-2, Issue-1, March 2012.
7. Shruti Gupta,ParteekKumar,"Comparative study of text to speech system for Indian language" ,International journal of advances in and information technology ISSN 2277–9140 April 2012.
8. Marian Macchi, Bellcore. "Issues in text-to-speech synthesis", In Proc. IEEE International Joint Symposia on Intelligence and Systems,pp. 318-325,1998.
9. Shreekanth. T , Udayashankara. V ,Arun Kumar. C "An Unit Selection based Hindi Text To Speech Synthesis System Using Syllable as a Basic Unit" IOSR Journal of VLSI and Signal Processing (IOSR-JVSP) Volume 4, Issue 4, Ver. II Jul-Aug. 2014.
10. Rajeswari K C and Uma Maheswari P. "Prosody Modeling Techniques for Text-to Speech Synthesis Systems". International Journal of Computer Applications 39(16):8-11, February 2012.
11. Rahul sawant, H. G Virani, Chetan desai ,"Personalized English speech synthesizer using Concatenative synthesis ",International journal of pure and applied research in engineering and technology . Research Article, IJPRET, 2013; Volume 1(8):260-267.
12. B. Sudhakar R. Bensraj Development of Concatenative Syllable based Text to Speech Synthesis System for Tamil International Journal of Computer Applications (0975 – 8887 Volume 91 – No 5, April 2014.

Hindi Tts Polysyllable Unit Concatenative Speech Synthesis Mos (mean Opinion Score)