A survey on methods of tts and various test for evaluating the quality of synthesized speech
International Journal of Development Research
A survey on methods of tts and various test for evaluating the quality of synthesized speech
Received 09th June, 2017; Received in revised form 24th July, 2017; Accepted 06th August, 2017; Published online 29th September, 2017
Copyright ©2017, Pravin M. Ghate and Shirbahadurkar. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
The main objective of the paper is give an ideal about different methods of the text to speech synthesis for quality of synthesized speech for Marathi Language. A system converting textual information into speech is usually called as Text to speech (TTS). Speech is surely the most natural mode of communication in human’s community. [Quartier, 2002]. This information can be evaluated at several non-exclusive stages of description. At the acoustic level, speech is considered as a mechanical wave that is an oscillation of pressure. The main claims of Speech Processing can be categorized as follows, Speech Recognition, Speech Synthesis, Speaker Recognition, Voice Analysis, Speech Enhancement, and Speech coding [Dutoit, 1997]. Out of the many application in this paper, speech synthesis is one of the discussion topic, Speech Synthesis: In Speech Synthesis, also called Text-to-Speech (TTS), the goal is to produce the speech, typically expressed in terms of naturalness and intelligibility of the produced voice.
