Statistical modelling of speech units in HMM-based speech synthesis for Arabic

International audience This paper investigates statistical parametric speech synthesis of Modern Standard Arabic (MSA). Hidden Markov Models (HMM)-based speech synthesis system relies on a description of speech segments corresponding to phonemes, with a large set of features that represent phonetic, phonologic, linguistic and contextual aspects. When applied to MSA two specific phenomena have to be taken in account, the vowel lengthening and the consonant gemination. This paper studies thoroughly the modeling of these phenomena through various approaches: as for example, the use of different units for modeling short vs. long vowels and the use of different units for modeling simple vs. geminated consonants. These approaches are compared to another one which merges short and long variants of a vowel into a single unit and, simple and geminated variants of a consonant into a single unit (these characteristics being handled through the features associated to the sound). Results of subjective evaluation show that there is no significant difference between using the same unit for simple and geminated consonant (as well as for short and long vowels) and using different units for simple vs. geminated consonants (as well for short vs. long vowels).