[Corpora-List] Query on Linking Text & Sound Files

From: Rita Carol Simpson (ritacsim@umich.edu)
Date: Thu Oct 17 2002 - 16:39:53 MET DST

  • Next message: Bruce L. Lambert, Ph.D.: "Re: [Corpora-List] Query on Linking Text & Sound Files"

    Dear Colleagues,

    Does anyone have first-hand experience with any tools or techniques for
    linking existing text transcripts of speech to sound files?

    Specifically, the MICASE project team is looking for input on how to go
    about linking the sound files (currently in mp3 format, but convertable
    to other formats) with the text transcripts, in relatively small
    increments, and deliver the sound files online along with the transcripts
    (which are already available online, via the website listed below).

    Ideally we would like to link the transcripts to the sound files in such a
    way that from any point in the transcript you could click on a sound file
    link and get to that portion of the transcript -- to the nearest, say,
    30-second or 1-minute increment. I realize the labor to do this for nearly
    200 hours of naturally-recorded speech may be significant, but we are
    prepared to hire a number of research assistants to do as much of the
    markup, chunking, & aligning tasks as possible.

    If you know of & have used any kind of software that will simplify or
    streamline this process at all, or have suggestions about how we might go
    about it, I would very much appreciate hearing from you.
    (I do have a copy of the CSAE project's SoundWriter program, but because
    I have not been able to find any documentation on it, I cannot properly
    evaluate it; I suspect, however, that it's not exactly suited to our
    goals -- specifically the eventual web-delivery aspect. If you've
    successfully used this particular program, I would be interested in
    finding out more about it.)

    I will be happy to post a summary to the list of any replies I get.

    Thank you in advance,

    Rita Simpson
    _________________________________________________________________________

    Rita Simpson, PhD.
    Project Director, Michigan Corpus of Academic Spoken English
    English Language Institute, University of Michigan TEL: 734-763-7133
    www.lsa.umich.edu/eli/micase/micase.htm www.hti.umich.edu/m/micase/
    _________________________________________________________________________



    This archive was generated by hypermail 2b29 : Thu Oct 17 2002 - 16:49:24 MET DST