Parallel Computing in Electrical Engineering, 2004. International Conference on (2000)
Aug. 27, 2000 to Aug. 30, 2000
Abdellah Yousfi , University of Mohamed First Oujda-Moroco
Abdelouafi Meziane , University of Mohamed First Oujda-Moroco
In this paper, we propose an improvement to the centisecond TLHMM model  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 of A. Meziane  and N. Suaudeau 
A. Meziane and A. Yousfi, "Introduction of the Speaking Rate in the Model of Speech Recognition," Parallel Computing in Electrical Engineering, 2004. International Conference on(PARELEC), Quebec, Canada, 2000, pp. 64.