Rupinderdeep Kaur, R.K. Sharma and Parteek Kumar, Thapar University, India

A Text-To-Speech (TTS) system is a computer application that is capable of converting typed text into speech. This paper contains description of working of a TTS system along with architecture of the system and various available TTS systems for Indian Languages with comparison of these systems on the basis of the methods used by them for speech synthesis. TTS system generally involves two steps, text processing and speech generation. Synthetic speech may be used in several applications, like, telecommunications services, language education, aid to handicapped persons, fundamental and applied research etc. TTS involves many challenges during the process of conversion of text to speech. The most important qualities expected from speech synthesis system are naturalness and intelligibility. The general architecture of a TTS system and different waveform generation methods are discussed in this paper. A scheme for developing a TTS system for Punjabi Language is also included in this paper.

TTS, Phonetics, Prosody, Speech Synthesis