Return to the archive index

Hardware Speech Systhesis

From: Lee Adamson <>
Date: Sat, 02 Jan 1999 19:47:51 -0500

All of this Z80 retro-stuff (among other things) got me thinking...

I don't think it would be too hard to build a hardware tts box.

The same guy who has the scanner got a voice playback and record chip
for christmas; I'd thought that perhaps diphones could be recorded to it
and played back selectively, but unfortunately it only plays back big
chunks.

IMHO, festival using 99% of my CPU for ~2sec is rather outrageous, as
the Amiga 2000 on the back porch (2Mb ram, 8MHz 68000, multitasking OS)
could do some very nice tts (and very quickly).

Therefore, I think that an 8bit processor doing dedicated systhesis
would work fine...  But I really don't know anything about speech
systhesis.  I'm 95% sure that I could build the hardware if someone can
write the software (plug plug)...

Ok, perhaps a phoenome systhesizer, 'cause a Z80 would have a hard time
finding enough RAM/ROM to store a lexicon in...

The Amiga will soon be hooked to my desktop, providing leightweight tts
via a serial cable and an AREXX script, but I think it would be a bit
heavy to be carting about on my back (not to mention the battery hit
:)...

--
Subcription/unsubscription/info requests: send e-mail with subject of
"subscribe", "unsubscribe", or "info" to 
Wear-Hard Mailing List Archive (searchable): http://wearables.ml.org

+Previous Message in Thread | Next Message in Thread

From Wear-Hard Mailing list Archive (WH)
Maintained by R. Paul McCarty

Archive created with babymail