[Accessibility] Sec2b Item 7: Text To Speech

Janina Sajka janina at rednote.net
Wed Sep 10 10:22:31 PDT 2003


I realize we had not concluded on the TTS item. So, here's another cut
at candidate text for our consideration.


	7.)	Text To Speech (TTS)


Interfaces based on synthesized text to speech (TTS) technology have proven a successful and powerful accomodation for users with various disabilities,
including persons who are blind or who have learning disabilities. A standard mechanism supporting numerous voices in numumerous languages, yet
providing a single, consistant interface to applications is prefered.

We propose to adopt or develop a standard API for TTS services capable of supporting numerous languages and including the abilityt to smoothly and
quickly switch among different languages and/or voices. This project will adopt or develop standardized mark up for spoken dialog, and provide an API
for TTS services, such as JSAPI.

People with disabilities benefit by a larger availibility of languages choices, many that may not be supported by assistive technologies today.
Providing a robust, reliable TTS interface supporting multiple voices will make it possible to facilitate the vast populations around the globe who
otherwise, might not soon participate in a tecnology based economy.

Janina Sajka writes:
> From: Janina Sajka <janina at rednote.net>
> 
> Hmmm, I think Bill has a good point here. I suspect I got my FSG a tad
> mixed up with funding prospects. In other words, I suspect tools for
> creating voices may well be out of scope--though probably much more
> fundable than writing service APIs. Ignoring, for the moment, the policy
> problem about backing a funding proposal that goes beyond the FSG
> interest, what is the FSG interest that we can and should propose?
> 
> Bill, if we took your phrase and put some internationalization around
> it, something like:
> 
> 
>  capable of supporting numerous languages and including the abilityt to
>  smoothly and quickly switch among different languages and/or voices."
>  
>   capable of supporting numerous languages and including the abilityt to
>   smoothly and quickly switch among different languages and/or voices."
>   
>   "Adopt or develop a standard API for TTS services capable of supporting
> numerous languages and including the abilityt to smoothly and quickly
> switch among different languages and/or voices."
> 
> 
> 
> Bill Haneman writes:
> > From: Bill Haneman <bill.haneman at sun.com>
> > 
> > Sharon:
> > 
> > "Standardize a TTS voice creation API" doesn't make sense to me, as far
> > as I know there are no APIs in existance for 'creating new voices' as
> > the phrase would ordinarily be understood. 
> > 
> > I'd try "promote a standard API for TTS services", and ignore the
> > difficult issue of voice creation.
> > 
> > If instead, by 'voice creation' you mean 'the instantiation of agents
> > capable of generating synthesized speech, at runtime', i.e. invoking
> > synthetic speakers, that is indeed something we intend to use API for.
> > 
> > - Bill
> > 
> > - Bill
> > ...
> > > Perhaps based on Bill's comments, the paragraph should be changed to:
> > > > We propose to
> > > > standardize a TTS voice creation API to simplify and systemetize the
> > > process of
> > > > creating new voices.  
> 
> -- 
> 	
> 				Janina Sajka, Director
> 				Technology Research and Development
> 				Governmental Relations Group
> 				American Foundation for the Blind (AFB)
> 
> Email: janina at afb.net		Phone: (202) 408-8175

-- 
	
				Janina Sajka, Director
				Technology Research and Development
				Governmental Relations Group
				American Foundation for the Blind (AFB)

Email: janina at afb.net		Phone: (202) 408-8175




More information about the Accessibility mailing list