Newsgroups: comp.speech
Path: pavo.csi.cam.ac.uk!doc.ic.ac.uk!daresbury!mrccrc!news.dcs.warwick.ac.uk!warwick!zaphod.crihan.fr!univ-lyon1.fr!swidir.switch.ch!scsing.switch.ch!xlink.net!howland.reston.ans.net!usc!cs.utexas.edu!utnut!torn!watserv2.uwaterloo.ca!watserv1!ming
From: ming@sunee.uwaterloo.ca (Ming Ho)
Subject: Time-domain speech
Message-ID: <CFM8AA.5Ms@watserv1.uwaterloo.ca>
Sender: news@watserv1.uwaterloo.ca
Organization: University of Waterloo
Date: Thu, 28 Oct 1993 16:25:21 GMT
Lines: 14

Does anyone know of researchers or of references that have studied
speech recognition directly from the time-domain signal rather than
from a transformation to the frequency-domain?

Has anyone ever seen a study of the pitch period pattern between
phonemes?

Thanks in advance for any information.

=================================================================
Ming Ho (ming@sunee.uwaterloo.ca)
Speech Recognition Group
Electrical & Computer Engineering
University of Waterloo, Canada
