Newsgroups: comp.speech
Path: pavo.csi.cam.ac.uk!warwick!pipex!howland.reston.ans.net!spool.mu.edu!sgiblab!wetware!spunky.RedBrick.COM!psinntp!hns!wliu
From: wliu@hns.com (Weimin Liu)
Subject: Re: speech, non-speech discrimination
Sender: news@hns.com (USENET news system)
Message-ID: <1993Dec28.214858.591@hns.com>
Date: Tue, 28 Dec 1993 21:48:58 GMT
References: <63442@ogicse.ogi.edu>
Organization: Hughes Network Systems, Inc.
Lines: 27

In article <63442@ogicse.ogi.edu> ldcolton@chico.cse.ogi.edu (L Don Colton)
writes:
...
>My cursory literature search on speech / non-speech in general (not
>limited to telephone speech) turned up only a very small handful of
>references (less than six, of varying antiquity). I am left to wonder
>whether
>
>  (a) this is too easy, so no one deems it important enough to write
>about, or
>
>  (b) this is too difficult, and no one knows how to do it, or
>
>  (c) this is written up in journals or proceedings that are outside
>my pitiful excuse for a literature search.

In my opinion, the answer is (b), too difficult as a general problem.
Putting it to the extreme, how do you distinguish speech from noise,
when the "noise" is another speech spoken by someone of the same
gender and pitch-frequency range?  I have no doubt, however, that the
problem can be substantially simplified, to the point where it's
trivial, if something about the noise is known.
-- 
Weimin Liu (B-251, x7086)
Advanced Development
HUGHES _N_e_t_w_o_r_k_ _S_y_s_t_e_m_s
Germantown, Maryland USA
