Sorry your browser is not supported!

You are using an outdated browser that does not support modern web technologies, in order to use this site please update to a new browser.

Browsers supported include Chrome, FireFox, Safari, Opera, Internet Explorer 10+ or Microsoft Edge.

DarkBASIC Discussion / text to speech program

Author
Message
philip2k
9
Years of Service
User Offline
Joined: 28th Aug 2010
Location:
Posted: 16th Oct 2010 13:28
I\'m trying to create a program to convert text to speech like a vocal synthetizer, I\'m using the load sound command to load the phonemes the basic briks of language,(in Itlian right now, but it works too in spanish) I\'m having some trouble with the sound duration to concatenate the sounds to form a word but i\'m improving on that, if any one is interested or have some advice or questions, I\'m here glad for your help to help me make it better, soon when I\'l get some better results I will up load it here.

leone.filippo@yahoo.it
Libervurto
14
Years of Service
User Offline
Joined: 30th Jun 2006
Location: On Toast
Posted: 16th Oct 2010 22:22 Edited at: 16th Oct 2010 22:23
Sounds interesting. Do you have an example of it saying something?

Latch
14
Years of Service
User Offline
Joined: 23rd Jul 2006
Location:
Posted: 18th Oct 2010 23:57
Quote: "I\'m having some trouble with the sound duration to concatenate the sounds to form a word but i\'m improving on that, if any one is interested or have some advice"


I'd be interested in seeing what you have so far. It sounds pretty cool.

Though I'm not sure how you are doing things, a suggestion for the sound duration would be in the loopability (made up word!) of the vowel sounds and the non-articulated parts of a consonant (like the breathy sound after a TH in English). Consonants are going to be short and hard for the most part, so if you loop them in their entirety you'll get clicks.

In DBC, if you use mp3s or other compressed audio formats , you run into the possibility of extended areas of no sound at the beginning of the file and the end of the file. So if you loop them, there can be just a small instance of silence that ruins the looping effect. So you might want to stick with .wav formatted sounds.

Enjoy your day.
Libervurto
14
Years of Service
User Offline
Joined: 30th Jun 2006
Location: On Toast
Posted: 19th Oct 2010 18:33
How are you recording the voice? Are you doing it yourself?
For each sound I would record a few slightly different examples with the sound in different parts of the words. For example, if we recorded the G "guh" sound I could say things like: "Gas", "Grass", "Glass", "Aggregate", "Long"

Then we can edit them and cut out the rest of the word around the G and see if there is a difference in the sound. "Long" is definitely different (not sure if this is a separate recognised phoneme) but there may be differences between the other G sounds that you could break them into sub-phonemes for a more fluid pronunciation.

I phoned up my phone company today and the generated voice on the other end was quite impressive, it sounded fluid even when reading back my name that I spelled out to it. I like to talk like a robot to those things, it seems to help and it's funny!


Do oranges know what colour they are?
SH4773R
10
Years of Service
User Offline
Joined: 18th Jan 2010
Location: AMERICA!!!
Posted: 25th Oct 2010 04:32
Sounds very cool I'm working on a simmalar project in dbpro

Login to post a reply

Server time is: 2020-08-13 19:03:37
Your offset time is: 2020-08-13 19:03:37