Sciweavers

Share
ACL
2000

Inducing Probabilistic Syllable Classes Using Multivariate Clustering

9 years 3 months ago
Inducing Probabilistic Syllable Classes Using Multivariate Clustering
An approach to automatic detection of syllable structure is presented. We demonstrate a novel application of EM-based clustering to multivariate data, exempli ed by the induction of 3- and 5-dimensional probabilistic syllable classes. The qualitative evaluation shows that the method yields phonologically meaningful syllable classes. We then propose a novel approach to grapheme-to-phoneme conversion and show that syllable structure represents valuable information for pronunciation systems.
Karin Müller, Bernd Möbius, Detlef Presc
Added 01 Nov 2010
Updated 01 Nov 2010
Type Conference
Year 2000
Where ACL
Authors Karin Müller, Bernd Möbius, Detlef Prescher
Comments (0)
books