Newsgroups: comp.speech
Path: pavo.csi.cam.ac.uk!doc.ic.ac.uk!warwick!uknet!pipex!howland.reston.ans.net!vixen.cso.uiuc.edu!uwm.edu!fnnews.fnal.gov!att-in!princeton!phoenix.Princeton.EDU!lseltzer
From: lseltzer@phoenix.Princeton.EDU (Linda A. Seltzer)
Subject: Re: Synthesised singing
Message-ID: <1994Jan4.033631.11661@Princeton.EDU>
Originator: news@nimaster
Sender: news@Princeton.EDU (USENET News System)
Nntp-Posting-Host: phoenix.princeton.edu
Organization: Princeton University
References: <9400411.7766@mulga.cs.mu.OZ.AU>
Date: Tue, 4 Jan 1994 03:36:31 GMT
Lines: 14

In article <9400411.7766@mulga.cs.mu.OZ.AU> bromage@mundil.cs.mu.OZ.AU (Andrew James BROMAGE) writes:
>I'd like to know if anyone has ever thought of synthesised a human voice
>singing? Has anyone tried it out and how did it turn out?
>
Perry Cook of Stanford's computer music lab (CCRMA) did a demo for the
NeXT machine in which a singing voice is synthesized using a waveguide
model.  I don't know whether he has published a paper describing his
algorithm - maybe there was something in the computer music journal.

Earlier than that, there was program called CHANT from IRCAM in Paris.

The output of Cook's program is nice for a lyrical voice quality.
It's not complex enough to produce singing of words and to get all
of the intonation right, etc.  I haven't heard the output of CHANT.
