Concatenative approach for Text-to-Speech

Concatenative approach for Text-to-Speech, Sangramsin N. Kayte, Monica Mundada and Suryakanth V. Gangashetty A Text-to-Speech (TTS) synthesis system is the artificial production of human speech. The TTS system converts ordinary orthographic text into an acoustic signal, which is indistinguishable from human speech. For developing a natural human-machine interface, the TTS system can be used as a way to communicate back, like a human voice by a computer. The TTS can be a voice for those people who cannot speak. People wishing to learn a new language can use the TTS system to learn the pronunciation. Text and voice models are given as input to this system, which in turn generates speech as an output corresponding to the given voice models. The TTS system can be used to read text from emails, SMSs, web pages, news, articles and so on. In such reading applications, the TTS technology can reduce the eye strain. Speech synthesis systems can be extremely useful to people who are visually challenged, visually impaired and illiterate to get into the mainstream society. The TTS systems can also be integrated to work with systems that recognize text from scanned documents.