Duration modelling and evaluation for Arabic statistical parametric speech synthesis

Sound duration is responsible for rhythm and speech rate. Furthermore, in some languages phoneme length is an important phonetic and prosodic factor. For example, in Arabic, gemination and vowel quantity are two important characteristics of the language. Therefore, accurate duration modelling is crucial for Arabic TTS systems. This paper is interested in improving the modelling of phone duration for Arabic statistical parametric speech synthesis using DNN-based models. In fact, since a few years, DNN have been frequently used for parametric speech synthesis, instead of HMM. Therefore, several variants of DNN-based duration models for Arabic are investigated. The novelty consists in training a specific DNN model for each class of sounds, i.e. short vowels, long vowels, simple consonants and geminated consonants. The main idea behind this choice is the improvement that we already achieved in the quality of Arabic parametric speech synthesis by the introduction of two specific features of Arabic, i.e. gemination and vowel quantity into the standard HTS feature set. Both objective and subjective evaluations show that using a specific model for each class of sounds leads to a more accurate modelling of the phone duration in Arabic parametric speech synthesis, outperforming the state-of-the-art duration modelling systems.