[FoRK] Voice Recognition (Training) Profiles

Albert S. albert.scherbinsky
Sat Oct 29 08:28:21 PDT 2005


The standard voice training file approach sounds like
it could work. The companies would just have to agree
on what needs to be said in the standard training
audio file. As you say, they are being trained with
voice samples anyway.

Standards usually emerge because of economic
necessity. A leader in the field decides to open it
up, and everyone else follows. The rational for the
leader to open it up is that by lowering the cost, and
increasing accessibility to the technology the market
as a whole grows. The rising tide lifts all boats.

Albert

--- "B.K. DeLong" <bkdelong at pobox.com> wrote:

> At 11:44 AM 10/28/2005, Reza B'Far wrote:
> >We're working on leveraging existing VR systems for
> speech transcription
> >(large vocabulary recognition).  What you're
> suggesting is not possible for
> >this.  Basically, there is no standard approach
> right now to speech
> >transcription.  The first step would be to come up
> with a standard approach
> >(which is not currently possible because the no one
> has invented/discovered
> >the canonical mathematical model).
> 
> Well, something like that may not be possible at the
> moment, but what 
> about coming up with a standard for storing
> syllables, letters or 
> words? Sure, the storage file would be absolutely
> huge to start with 
> but if vendors at least agreed to allow
> import/export of a standard 
> audio training set then perhaps we can at least get
> users 3/4 of the 
> way there without having to repeat the entire
> process with each program.
> 
> I wonder if that's even possible without violating
> current patents. 
> Do you know how various current VR programs handle
> voice training?
> 
> Thanks.
> 
> 
> 
> --
> B.K. DeLong
> bkdelong at pobox.com
> +1.617.797.8471 (Note new number)
> 
> http://www.brain-stream.com               Play.
> http://www.bostonredcross.org            Volunteer.
> http://www.the-leaky-cauldron.org        Potter.
> http://www.hackerfoundation.org          Future.
> http://www.wkdelong.org           Son.
> 
> 
> PGP Fingerprint:
> 38D4 D4D4 5819 8667 DFD5  A62D AF61 15FF 297D 67FE
> 
> FOAF:
> http://foaf.brain-stream.org 
> 
> _______________________________________________
> FoRK mailing list
> http://xent.com/mailman/listinfo/fork
> 



More information about the FoRK mailing list