В Птн, 21/12/2007 в 14:13 -0200, Marcelo Yassunori Matuda пишет: > Hi, > > I wrote an ***experimental*** C++ program that uses the Tube > Resonance Model and the file diphones.mxml (articulation data) from > Gnuspeech. > > Apart from the tube model, it is not a translation of the Gnuspeech > ObjC code, so the quality of speech output is not the same. > > It may be used as a voice in Festival. Festival is needed if you want > to use the program as a TTS system. > > You may download it at: http://sourceforge.net/projects/dvagar > > This is for us mere mortals who can't use Gnuspeech... :)
Hi Marcelo Amazing work! I think it's a real future of gnuspeech with all festival framework I hope it will get great progress. A few comments: 1. Please check for xerces-c in configure and add it as a dependency 2. Could you provide a sample of synthesis, like this one I've just got with your program: http://festlang.berlios.de/docu/lib/exe/fetch.php?id=gnuspeech&cache=cache&media=examples:gnuspeech-sample.wav 3. What about announcement on festival-talk? It would be nice to get this announced on gnuspeech website and integrated into festival as well. I know many of us wrote compatibilty code like this to make gnuspeech at least work on linux.
signature.asc
Description: Эта часть сообщения подписана цифровой подписью
_______________________________________________ gnuspeech-contact mailing list [email protected] http://lists.gnu.org/mailman/listinfo/gnuspeech-contact
