Building Synthetic Voices | ||
---|---|---|
<<< Previous | Diphone databases | Next >>> |
The easiest way to define a voice is to start from the skeleton scheme files distributed. For English voices see the Chapter called US/UK English Diphone Synthesizer, and for non-English voices see the Chapter called A Japanese Diphone Voice for detailed walkthroughs.
Although in many cases you'll want to modify these files (sometimes quite substantially), the basic skeleton files will give you a good grounding, and they follow some basic conventions of voice files that will make it easier to integrate your voice into the Festival system.
<<< Previous | Home | Next >>> |
Building LPC parameters | Up | Checking and correcting diphones |