(276) previous ~ index ~ next

To: James Allan <allan@cs.umass.edu>,
From: "Strzalkowski, Tomek (CRD)" <strzalkowski@crd.ge.com>
Subject: RE: index file choices
Date: Thu, 17 Dec 1998 23:48:28 -0500

As far as I can say, FDCH is a true manual transcript (or as close to one
as we can get) while CCAP is a degraded manual transcript. Thus lacking
anything better CCAP could do as a poor substitute, but I see no reason
why it should be used as manual if FDCH is available. Since we are interested
in performance contrasts, both FDCH vs. ASR and CCAP vs. ASR are of
interest, although for somewhat different reasons. For me, manual = FDCH.
But of course, George has the final word.

--- Tomek

> ----------
> From: George Doddington[SMTP:doddington@nist.gov]
> Reply To: doddington@nist.gov
> Sent: Thursday, December 17, 1998 6:11 PM
> To: James Allan
> Cc: tdt-distrib@ldc.upenn.edu
> Subject: Re: index file choices
>
> James Allan wrote:
>
> > TDTers,
> >
> > I don't find an answer to this question in the eval information,
> > so.... There are three sets of index files provided for tracking:
> >
> > trk_nwt_man_ccap
> > trk_nwt_man_fdch
> > trk_nwt_asr
> >
> > According to the documentation, these represent the three source
> > conditions. But in the eval plan, the three source conditions are:
> >
> > manual transcription
> > automatic transcription
> > sampled data signal
> >
> > So there really isn't an index for the sampled data signal, and the
> > trk_nwt_asr clearly goes with "automatic transcription". But which of
> > the to trk_nwt_man_xxx runs is supposed to go with "manual
> > transcription"? Both? A random choice? It doesn't matter because
> > deep down they're the same?
> >
> > The same questions occur for the detection task (and the segmentation
> > task, I suppose).
> >
> > Thanks.
> > -- james
>
> The answer is:
> manual transcription => ccap
> automatic transcription => asr
> sampled data signal => (not represented)
>
> (fdch is a special case of manual transcription)
> --
> George Doddington at NIST: doddington@nist.gov or 301/975-3261
>
>
(276) previous ~ index ~ next

Last updated Wed Feb 3 10:44:19 1999