OXIGEN
The OXford IntonationGENerator
A quantitative model of Intonational Variation in the British Isles
UK Economic and Social Research Council
Award RES-000-23-0149
University of Oxford Phonetics Laboratory
May 2003 - April 2005
Principal Investigators:
Esther Grabe and
John Coleman
Associated Research Fellow: Greg Kochanski
Summary of Research
In this project we shall investigate variation in English intonation,
insofar as it is represented in an existing corpus containing recordings
of nine dialects of English. Whereas prior models of intonation focus
on a single dialect and style, we shall construct a statistical computational model of intonation which takes account of variation due
to dialect, speaking style, gender and individual speaker habits.
The model will be useful for the UK speech technology
industry. Developers of automatic speech synthesis and recognition systems
require linguistically rich yet quantitative models of intonation
because current systems cannot produce or recognise the intonation
patterns of different English dialects, styles or speakers. Our work
will also be valuable for speech therapists, for whom we shall prepare
an informative leaflet, and for English language teachers.