12 June: Steve Greenberg -- BMonday, June 17, 11:45 (UCD)
Dublin Computational Linguistics Research Seminar: Index of June 2002 | Dublin Computational Linguistics Research Seminar - Index of year: 2002 | Full index
Subject: Talk by Steve Greenberg (ICSI Speech Group)
Dear All,
Steve Greenberg of the ICSI Speech Group at Berkeley will be giving a
talk entitled "Beyond the Phoneme: A Juncture-Accent Model of Spoken
Language" at UCD (Computer Science Building, Room B1.09) on Monday
17th June at 11.45. The abstract is given below.
I appreciate that this is holiday time for many of you but since Steve
is managing to combine his visit with a conference trip to Europe,
this was the only time possible. I hope we can still get a large
audience for his talk.
Best regards,
Julie
p.s. apologies if you receive this message more than once.
Beyond the Phoneme: A Juncture-Accent Model of Spoken Language
Steven Greenberg
International Computer Science Institute
1947 Center Street, Berkeley, CA 94704
Current-generation speech recognition systems generally represent
words as sequences of phonemes. This "phonemic beads on a string"
approach is based on a fundamental misconception about the nature of
spoken language and makes it difficult (if well-nigh impossible) to
accurately model the pronunciation variation observed in spontaneous
speech.
Five hours of spontaneous dialogue material (from the Switchboard
corpus) has been manually labeled and segmented, and a subset of this
corpus has been manually annotated with respect to stress accent
(i.e., the prosodic emphasis placed on a syllable). Statistical
analysis of the corpus indicates that much of the pronunciation
variation observed at the phonetic-segment level can be accounted for
in terms of stress-accent pattern and position of the segment within
the syllable.
Such analyses imply that spoken language can be thought of as a
sequence of accent peaks (associated with vocalic nuclei) separated by
junctures of variable type and length. These junctures are associated
with what are generally termed "consonants" D0 however, many
consonants do not behave as segments proper, but rather serve to
define the nature of the separation (i.e., juncture) between adjacent
syllables.
A "juncture-accent" model (JAM) of spoken language has interesting
implications for auditory models of speech processing as well as
consequences for developing future-generation speech recognition
systems.
------------------------------------------------------------------
___
| | \ | Dr. Julie Berndsen
| O / Department of Computer Science,
_ | | \ University College Dublin, Belfield, Dublin 4, IRELAND
| V O | Phone: +353 1 716 2493, Email: Julie.Berndsen@ucd.ie
\__/__/ WWW: http://www.cs.ucd.ie/staff/berndsen/
Research Group WWW: http://thistle.ucd.ie/CLISTE
-----------------------------------------------------------------
Dublin Computational Linguistics Research Seminar - Index of June 2002 | Index of year: 2002 | Full index