Speech synthesis is the artificial production of human voice. A computer system used for this task is called a speech synthesizer. Anyone can use this synthesizer in software or hardware products. The main aim of text-to-speech (TTS) system is to convert normal language text into speech. Synthesized speech can be produced by concatenating pieces of recorded speech that are stored in a database. TTS Systems differ in size of the stored speech units. A system which stores phones or diphones provides the largest output range, but this may give low clarity. For specific application domains, the storage of entire words or sentences allows for highquality output. Alternatively, a synthesizer can constitute a model of the vocal tract and other human voice characteristics to create a fully synthetic voice output. The quality of a speech synthesizer is decided by its naturalness or simillarity to the human voice and by its ability to be understood clearly. This paper summarizes the published literatures on Text to Speech (TTS), with discussing about the efforts taken in each paper. This system will be more helpful for an illiterate and visually impaired people to hear and understand the text.
[1]
Hema A Murthy,et al.
Design and Development of a Text-To-Speech Synthesizer for Indian Languages
,
.
[2]
Junichi Yamagishi,et al.
Synthesis of fast speech with interpolation of adapted HSMMs and its evaluation by blind and sighted listeners
,
2010,
INTERSPEECH.
[3]
Tohru Ifukube,et al.
A new touchscreen application to retrieve speech information efficiently
,
2013,
IEEE Transactions on Consumer Electronics.
[4]
Alan W. Black,et al.
Flite: a small fast run-time synthesis engine
,
2001,
SSW.