出版社:Academy & Industry Research Collaboration Center (AIRCC)
摘要:A Text-To-Speech (TTS) system is a computer application that is capable of converting typedtext into speech. This paper contains description of working of a TTS system along witharchitecture of the system and various available TTS systems for Indian Languages withcomparison of these systems on the basis of the methods used by them for speech synthesis. TTSsystem generally involves two steps, text processing and speech generation. Synthetic speechmay be used in several applications, like, telecommunications services, language education, aidto handicapped persons, fundamental and applied research etc. TTS involves many challengesduring the process of conversion of text to speech. The most important qualities expected fromspeech synthesis system are naturalness and intelligibility. The general architecture of a TTSsystem and different waveform generation methods are discussed in this paper. A scheme fordeveloping a TTS system for Punjabi Language is also included in this paper.