| | |
Summary: DATA-DRIVEN PRONUNCIATION MODELLING FOR NON-NATIVE
SPEAKERS USING ASSOCIATION STRENGTH BETWEEN PHONES
Ingunn Amdal£
, Filipp Korkmazskiy and Arun C. Surendran
Multimedia Communications Research Laboratory
Bell Labs, Lucent Technologies
Murray Hill, NJ 07974, USA
amdal@tele.ntnu.no, yelena,acs @research.bell-labs.com
ABSTRACT
In this paper we present an approach to modelling pronuncia-
tion variation, particularly for non-native speakers, by modifying
the lexicon. In this way we can model several speakers simultane-
ously, i.e. use the same lexicon and the same acoustic models for
all speakers. We use a data-driven approach, i.e. methods based
solely on the reference lexicon, the recognizer's acoustic models,
and the acoustic data.
We propose a new alignment procedure using an estimated rela-
tion measure between the phones in the reference transcription and
in the alternative transcription of the new speaker data. This mea-
sure discovers statistically significant correspondence between the
|
