Alan Stockdale wrote
> Imagine importing a transcript and even before you start coding the QDA
> program is aware of all the different speakers and their properties, and
> knows which speaker is associated with which speech turn.
Playing around with Transcribers demo I noticed that using a stereo
recording in a two-person setting you can identify turns visually from the
waveform-graphics. I think this could be automated quite easily.
Having tie-clip microphones on all participants this could be extended to
group interviews if there were software to support several microphones.
With just one audio-stream one would need automatic speaker-recognition, but
a search on automatic-speaker-recognition suggests that this is not
practical yet.
I think that the waveform-graphics on Transcriber and Transana is a big
bonus when comparing them with f4.
I hope to find some time to do some work along these lines (automatic
turn-recognition on multi-microphone systems)
-Timo
P.S I read qual-software in digest format. The fact that many contributors
use html-formatting in their mail these days makes the digest very difficult
to read. Please take a look at eg.
http://www.birdhouse.org/etc/evilmail.html and consider turning htlm- or
rich-text formatting of in your mail-client.
|