Continue to Site

Welcome to EDAboard.com

Welcome to our site! EDAboard.com is an international Electronics Discussion Forum focused on EDA software, circuits, schematics, books, theory, papers, asic, pld, 8051, DSP, Network, RF, Analog Design, PCB, Service Manuals... and a whole lot more! To participate you need to register. Registration is free. Click here to register now.

Text To Speech Converter

Status
Not open for further replies.

shah11

Newbie level 3
Joined
Apr 22, 2011
Messages
4
Helped
0
Reputation
0
Reaction score
0
Trophy points
1,281
Activity points
1,302
Hello .

Brothers i am doing a project on text to speech converter but i have problem of jerks in the output of that system . Means when i concatenate the phonemes it seems like it is speaking all phonemes differently not a word . Can any friend give me any solution of this problem..........
 

I once read an article saying this problem is typical of computerized speech.

It said the solution is that you need to spell certain words precisely, in order to get the computer to pronounce them the same way we do.

Example, to make vowels sound long enough.

The spellings often look strange.
 
I do that bro but as i do not have waves of phonemes and i save them on my own using a simple mike so it doesn't effect too much..
 

you can use Diphones instead of phonemes.. but Its very hard work to make diphones..

other solution is try to change the shape of envelope in individual phonemes according to the word that you going to speak.. :-D
 

Status
Not open for further replies.

Part and Inventory Search

Welcome to EDABoard.com

Sponsor

Back
Top