[MUD-Dev] online voice communication

[Amanda Walker]

On 11/27/02 11:39 PM, Dave Trump <trump at trumps.net> wrote:

> Also if you were willing to invest quite a bit of time and effort
> into the project it should be possible to use tiny wav files for
> each sound, blending them before playback.

This is the basic approach taken by the current benchmark technique
for speech synthesis, TD-PSOLA (Time Domain Pitch Synchronous
Overlap and Add).  It's used by the open source "Festival" speech
synthesis system, for example.

Amanda Walker


_______________________________________________
MUD-Dev mailing list
MUD-Dev at kanga.nu
https://www.kanga.nu/lists/listinfo/mud-dev