[MUD-Dev] [TECH] Voice in MO* - Phoneme Decomposition and Reconstruction

[Rudy Neeser]

Hi All

I don't have much experience with speach-to-text and text-to-speach
technology, but I do have a concern: as far as I am aware,
speach-to-text software isn't currently at a level where it can
understand the different ways that a large and varied group of
people can pronounce the same language.

For instance, if you want some STT software to operate for people
from both the south of France and from New York (just pulled those
places out of a hat), then the software will need to have enough
data to recognise the same english words being pronounced
differently by these two different groups of people.

If your mud is going to have STT software in the client, then
somehow it will have to recognise the words being pronounced by an
extremely large and varied group of people (assuming you want an
international population playing). This is a massive data entry
task.

Anyway, like I said, I've next to no experiece with STT software
(I've only got limited experience in syntactic theories of the
Chomskian / MIT mold -- i.e. P&P and MP -- and next to none with
phonology). So if anything I said here is way off the bat, I
apologise.

-- Rudy


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