Click here to register.

Acoustic Model Discussions

Flat
Using the Models as source for speech "synthesis"
User: Visitor
Date: 4/4/2007 2:52 pm
Views: 576
Rating: 7    Rate [

+

]

As we are building models to be used as HMM for the recognizer, is there a way to use them to actually do TTS ?

I'm a bit new to the subject so apologies if the question seems stupid.

thanks! 

--- (Edited on 4/ 4/2007 2:52 pm [GMT-0500] by Visitor) ---

Reply
Re: Using the Models as source for speech "synthesis"
User: kmaclean
Date: 4/5/2007 8:45 am
Views: 288
Rating: 11    Rate [

+

]

Hi,

The HTS project (an HMM-based Speech Synthesis System) uses Hidden Markov Models to generate speech.  The HTS engine can be used with version 2.0 of the  Festival Text to Speech System.

Ken 

--- (Edited on 4/ 5/2007 9:45 am [GMT-0400] by kmaclean) ---

Reply
Add