Campus Event Calendar
Event Entry
What and Who
Human and Machine Idetification of Transitional Speech Segments
Andrew Morris
Speech and Hearing Research Group, Sheffield University, England
AG 1, AG 2, AG 3, INET, AG 4, AG 5, D6, RG1, SWS
AG Audience
English
Note: We use this to send email in the morning.
Date, Time and Location
Monday, 25 November 96
15:00
60 Minutes
17.2 - Computerlinguistik
Raum 5.09
Saarbrücken
Abstract
While the phoneme is generally accepted as the basic recognition unit
in large vocabulary isolated word automatic speech recognition, in
continuous speech recognition phonetic target undershoot often leeds to
poor phoneme definition. It is now established that phoneme transitions
can provide a complementary set of speech units which are less prone to
the effects of context and coarticulation, but as yet we do not have a
clear understanding of the phonetic invariants which these transitions
provide. In this talk I will describe and present the results from
some human perception and machine recognition experiments which we have
designed specifically to analyse the phonetically relevent information
for consonantal place of articulation in a multilingual set of VC and CV
transitions.
in large vocabulary isolated word automatic speech recognition, in
continuous speech recognition phonetic target undershoot often leeds to
poor phoneme definition. It is now established that phoneme transitions
can provide a complementary set of speech units which are less prone to
the effects of context and coarticulation, but as yet we do not have a
clear understanding of the phonetic invariants which these transitions
provide. In this talk I will describe and present the results from
some human perception and machine recognition experiments which we have
designed specifically to analyse the phonetically relevent information
for consonantal place of articulation in a multilingual set of VC and CV
transitions.
Contact
Ralf Benzm"uller, FR 8.7 Phonetik/Phonologie, 66041 Saarbrücken
Tel. 0681/ 302 4689 Fax.: 0681/302 4684
--email hidden
passcode not visible
logged in users only
Tags, Category, Keywords and additional notes