Searching \ for 'State of the Art artificial voice box AGSC' in subject line. ()
Make payments with PayPal - it's fast, free and secure! Help us get a faster server
FAQ page: www.piclist.com/techref/io/audio.htm?key=voice
Search entire site for: 'State of the Art artificial voice box AGSC'.

Truncated match.
PICList Thread
'State of the Art artificial voice box AGSC'
2006\01\20@155455 by Russell McMahon

face
flavicon
face
>I have been looking at Internet information regarding
> electronic voice box prosthetics.  the sound samples sound
> kind of okay.  What is the best that can be expected at this
> time and does anyone produce a unit that allows the user
> to control pitch and inflection with some kind of had-held or
> whatever.

Answering the general question re natural sounding speech synthesis,
rather than the specific question re prosthetics, the best synthesised
voices are now extremely good. Good enough that some people would
completely not notice that they are synthesised some of the time.
(Barnum's dictum - "... you can fool some of the people some of the
time, ... " :-) ).

There are numerous approaches but a promising one is the use of
diphones based on sampled genuine speech which are used as the basis
for hinting and rules which add the inflections necessary to make the
speech sound real.

One such is the MBrola project (pronounced "em-brola")(like "umbrella"
but different :-)).

       http://mambo.ucsc.edu/psl/mbrola/
or
       http://tcts.fpms.ac.be/synthesis/mbrola.html
or ...

I'll let them speak for themselves (pun intended):

   The aim of the MBROLA project, initiated by the TCTS Lab of the
Faculté Polytechnique de Mons (Belgium), is to obtain a set of speech
synthesizers for as many languages as possible, and provide them free
for non-commercial applications. The ultimate goal is to boost
academic research on speech synthesis, and particularly on prosody
generation, known as one of the biggest challenges taken up by
Text-To-Speech synthesizers for the years to come.
Central to the MBROLA project is MBROLA, a speech synthesizer based on
the concatenation of diphones. It takes a list of phonemes as input,
together with prosodic information (duration of phonemes and a
piecewise linear description of pitch), and produces speech samples on
16 bits (linear), at the sampling frequency of the diphone database
used (it is therefore NOT a Text-To-Speech (TTS)synthesizer, since it
does not accept raw text as input). This synthesizer is provided for
free, for non commercial, non military applications only.

Diphone databases tailored to the Mbrola format are needed to run the
synthesizer. A French voices have been made available by the authors
of MBROLA, and the MBROLA project has itself been organized so as to
incite other research labs or companies to share their diphone
databases.

_______________________



More... (looser matching)
- Last day of these posts
- In 2006 , 2007 only
- Today
- New search...