voice recognition

Posted by Michael Mandiberg | Mon Jan 6th 2003 1 a.m.

http://theredproject.com/voicerecognition

I use voice recognition software to dictate a lot. Sometimes i get phonecalls in the middle and the microphone is still on and the software keeps (mis)recording.

(07.26.02)
A conversation with my mother about my dying family dog:

a a a motion a are written an aria newsletter, a national Diet and rights and when your written right timing
, euros image of a long immune
From one of
The an engine in American euros are at uniform a result of the three of. And wrote Roe school in your own farmers to grow get my financial of nation copy me and Sundays jury rejected carry yet but one of my question is if I choose to buy a ticket in hours achieved right to it is the English interests are Ticketron one unprecedented contract is a matter what the airport market in recent price rise of what why I call you but when you call right here around after two interest-rate and when I hear a thing of Rwanda zillion know the enemy back then me on Iraq after to only gone all the runs ex-Soviet. Yet
  • Jim Andrews | Mon Aug 29th 2005 5:15 p.m.
    anyone familiar with the state of voice recognition software?

    more particularly, suppose you put a couple of omni-directional mics at a
    table at a coffee shop. can voice recognition now recognize words spoken by
    people who have not trained the voice recognition system?

    would be nice for a dbcinema installation piece, ie, one or more projectors
    reacting to a conversation.

    ja
    http://vispo.com/dbcinema
  • Jim Andrews | Tue Aug 30th 2005 2:59 p.m.
    > something like this?
    >
    > http://www.bek.no/gif/easylistening.htm
    >
    > hx

    nice. yes, related. in this public situation, was there much accuracy
    possible in its recognitions? i don't need it to recognize everything. or
    even much. but i do need it to be fairly accurate in what it does recognize.
    i don't need 100%. but people have to be able to see that their conversation
    and the images are related. the stronger the relation, the better. so the
    system just needs to be able to accurately recognize, say, one word every
    few seconds and throw out the words it's not real sure about. would be nice
    to have quite a large vocab. at least a couple of thousand words. sound
    doable within what is currently possible in a public space? i'm thinking it
    is possible. people won't have microphone headsets. same sort of situation
    as in your piece. only the recognitions will be fed into
    http://vispo.com/dbcinema .

    you used open source linux voice recognition software?

    how was the reaction to the piece?

    ja
Your Reply