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) ---
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) ---