Newsgroups: comp.speech
Path: pavo.csi.cam.ac.uk!warwick!pipex!uunet!cs.utexas.edu!sdd.hp.com!swrinde!network.ucsd.edu!munnari.oz.au!titan!dion.trl.oz.au!duke
From: duke@dion.trl.oz.au
Subject: Re: speaker recognition
Message-ID: <1993Mar29.141423.1@dion.trl.oz.au>
Lines: 20
Sender: root@trl.oz.au (System PRIVILEGED Account)
Organization: Telecom Research Laboratories, Melbourne, Australia
References: <3057@irit.irit.fr>
Date: Mon, 29 Mar 1993 19:14:23 GMT

In article <3057@irit.irit.fr>, joly@cerise.irit.fr (Philippe JOLY) writes:
> Could someone direct me to an ftp site where i can find
> something about SPEAKER RECOGNITION .
> (I'm trying to find automatically when actors are playing in 
> a part of a movie .)
> 


Speaker recognition has two main fields: speaker verification and speaker
identification.  The former is used by cooperative speakers to gain access
to some service, and would not be useful to you.  The latter is normally the
domain of forensic science (e.g. determining whether a suspect was involved in
a threat or conspiracy over the phone) and is a more difficult task.  I would 
be surprised if you found anything useful on ftp sites.  I suggest you look 
for papers or seek experts in the forensic science area as well as specialist
speech activities.

Peter Duke
p.duke@trl.oz.au

