期刊名称：International Journal of Mathematics and Mathematical Sciences
印刷版ISSN：0161-1712
电子版ISSN：1687-0425
出版年度：2002
卷号：29
DOI：10.1155/S0161171202010141
出版社：Hindawi Publishing Corporation
摘要：We propose an improvement to the centisecond TLHMM model
(Meziane, 1999) applied to the sound duration. Indeed, the
distribution of the sound duration depends on the speaking rate.
An adaptation in a post-processing step is needed. This
adaptation is studied by proposing a model of the speaking rate
based on average syllabic duration. The experiments elaborated on
a set of BDSONS show the interest of this approach.
This work is a continuation of those by Meziane (1999) and
Suaudeau (1994).
