Speech synthesis is an area in which research is being carried out by the Austrian Research Institute for Artificial Intelligence (OFAI).
We can point out the explanation that Wikipedia gives about this topic. Speech synthesis is the artificial production of human speech. A computer system used for this purpose is called a speech synthesizer, and can be implemented in software or hardware. A text-to-speech (TTS) system converts normal language text into speech; other systems render symbolic linguistic representations like phonetic transcriptions into speech.
Synthesized speech can be created by concatenating pieces of recorded speech that are sotred in database. Systems differ in the size of the stored speech units. A synthesizer can incorporate a model of the vocal track and other human voice characteristics to create a completely «synthetic» voice output.
Thierry Dutoit explains that the ultimate goal of a text-to-speech (TTS) synthesizer is to read any text, whether it was directly introduced in the computer by an operator or scanned and submitted to an optical character recognition (OCR) system. Reading should be intelligible and natural.
In reference to the definition of text-to-speech systems Dutoit points out that specific talking machines termed as voice response systems produce artificial speech by simply concatenating isolated words or parts of sentences. They are, however, applicable only when a limited vocabulary is required and when the sentences to be pronounced share a very restricted structure, as is the case for the announcement of arrivals in train stations, for instance. In the context of TTS synthesis, it is impossible to record and store all the words of the focus language. It is thus more suitable to define text-to-speech as the production of speech by machines, by way of automatic phonetization of the sentences to utter.
Sources:
*Speech synthesis. (2008, April 10). In Wikipedia, The Free Encyclopedia. Retrieved 14:04, April 13, 2008, from http://en.wikipedia.org/w/index.php?title=Speech_synthesis&oldid=204741034
*Thierry Dutoit. «An Introduction to Text-to-Speech Synthesis». Published in 1997, Springer. 285 pages. Retrieved 13:46, April 13, 2008 from http://books.google.com/books?hl=en&lr=&id=bTmWkXi1e90C&oi=fnd&pg=PR13&dq=an+introduction+to+text-to-speech+synthesis&ots=Ik9kl1XoPC&sig=dYqHTVQuexMyMU0OxUbOoNKSJg0
The Beginning of the End 
In the upcoming presidential election, the ‘energy crisis’ sits in center stage. While there are certainly other issues on that stage that collectively affect our nation’s economy, alternative fuels and various other means http://gidromolot.vacau.com of creating energy for the next generation are significant factors in such a huge equation. No one can deny this notion and it is because of this that LEED reference manual may just be a guide to continued profits in the construction industry.
By: Usergesnurino on abril 1, 2013
at 12:48 am