Newsgroups: comp.speech
Path: pavo.csi.cam.ac.uk!pipex!uunet!zaphod.mps.ohio-state.edu!darwin.sura.net!mlb.semi.harris.com!travis.csd.harris.com!grouper!amber!tom
From: tom@ssd.csd.harris.com (Tom Horsley)
Subject: Non-realtime speech transcription?
Organization: Harris Computer Systems Division
Date: Mon, 25 Jan 1993 14:03:38 GMT
Message-ID: <TOM.93Jan25090338@amber.ssd.csd.harris.com>
Lines: 29
Sender: news@grouper.mkt.csd.harris.com (Network News)

An awful lot of the stuff in this group seems to be concerned with realtime
speech recognition (which is understandable, since it would be so useful),
but I am curious to know if there has been any research or actual
development of systems which can do a *really* good job of generating
transcripts of multi-speaker conversations, even if it can't be done in real
time (for instance, taking overnight to transcribe a 1/2 hour recording
would not be too unreasonable).

With all the organizations selling transcripts of news programs and all the
government spooks doing covert recordings, you would think that this
"transcript generation" problem would be one undergoing active research.

If anyone can point me at papers or products concerned with this area of
speech recognition, I would appreciate the information.
--
======================================================================
domain: tahorsley@csd.harris.com       USMail: Tom Horsley
  uucp: ...!uunet!hcx1!tahorsley               511 Kingbird Circle
                                               Delray Beach, FL  33444
+==== Censorship is the only form of Obscenity ======================+
|     (Wait, I forgot government tobacco subsidies...)               |
+====================================================================+
