[Top][All Lists]

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [Accessibility] Call to Arms

From: Christian Hofstader
Subject: Re: [Accessibility] Call to Arms
Date: Wed, 28 Jul 2010 11:59:17 -0400
User-agent: Mozilla/5.0 (X11; U; Linux i686; en-US; rv: Gecko/20100527 Thunderbird/3.0.5

On 07/27/2010 12:57 PM, Richard Stallman wrote:

rms: Need a first step for this whole process should be collecting a corpus for
     training and experimenting with different recognition parameters.

rms: This is something our community should be able to help with.
It needs someone to take the lead.

rms: ISTR reading about a project of that general nature.  I hope Chris
remembers the details.  I think it needed some practical support work.
Would you or someone else like to help?

cdh: I have an ever growing file of items related to voice recognition. I think one of the coolest ideas came from rms who suggested that we send people a corpus and have them record themselves reading it. We then use these recordings to train speech recognition engines and see how the results work out. This is slightly cumbersome for blind people without braille displays as they will need the synthesizer to tell them what to say in chunks small enough to be memorable but not cause pauses that are too long in their recordings. Of course, this task is easy and we can ask our friends from all walks of life to read a page or two short story and send us their wave file. Pretty much everyone can do this so asking our friends and relatives outside the hacking world will have as much value as anyone else.

cdh: SOmeone, name somewhere in my notes, volunteered to run the training software using these recordings to see what we can find.

cdh: I think we need to learn some details on how widely the range of accents we can accept varies. For instance, do most people need to speak with a relatively "standard" US accent or do our friends up in Harlem and down in Mississippi need to be excluded?

cdh: Can we make variant engines based on whether the speaker has a blackcent, a serious southern accent, a latino accent, etc.?

cdh: Since the call for arms, speech recognition has, by far, been the hottest topic regarding our project priorities. If I had to bet, I'd have thought it would have been Firefox and OpenOffice with orca.

cdh: I'll be in this motel until Friday when we start our drive north to our Cambridge residence and I'll be online a lot. Can someone volunteer to help collaborate with me on writing a two or three page project proposal that will help list the tasks related to speech recognition, skills of volunteers, existing components and help me find a person to lead the accessibility speech-recognition project? We will, of course, put this document out for comment on this list to refine it but, as I said in my original call to arms mail, it's time to get hacking.


Accessibility mailing list

Happy Hacking,

Christian Hofstader
Director of Access Technology
FSF/Project GNU,
GNU's Not Unix!

reply via email to

[Prev in Thread] Current Thread [Next in Thread]