[MUD-Dev] Speech to Text, etc. (was: On socialization and convenience )

[John Buehler]

Eli Stevens writes:

> One limitation of STTTS (heh heh) is that the intermediate form of
> communication is text.  I know that seems obvious, but I only
> point it out because it seems rather assumed, and it shouldn't be.
> What if the intermediate form was an entry into a lookup table of
> various sounds (not mapped directly to letters per se)?

Some TTS systems permit markers to be placed into the text in order
to play around with emphasis and such.  I was focusing on an
incremental step beyond having to read text on the screen because of
the practical problems associated with it - such as having to read
text instead of watching what's going on in the game world.  It's
not clear to me how much voice acting players want to toy with.
Good STT systems might be able to encode those emphasis marks to
retain the most critical tones.

> Combined with some sort of dual translation system (don't really
> know how you would set this up), you could have 35 y.o. men
> speaking like the dainty elven maidens they are pretending to be,
> or put a rough dwarven edge on a 13 y.o. boy's voice.  Maybe the
> SOM winner could be an index into a second table that is generated
> based on how your character sounds, with appropriate
> modifications.

Multiple voices is a place that the TTS systems haven't impressed me
much.  I've heard good female and male voices from the same system,
but I would want some kind of spectrum that the player could dink
around with to shape a voice that they like for their character.
Not unlike a color wheel.  But I don't even know if multiple voices
are necessary in a first use of the technique.  If everything was
read to the player in a single voice (or just male and female), it
still might be better than having to read the text.

JB

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