Duration modeling is a key task for every parametric speech synthesis system. Though such parametric systems have been adapted to many languages, no special attention was paid to explicitly handling Arabic speech characteristics. Actually, in Arabic phoneme duration has a distinctive role, because of consonant gemination and vowel quantity. Therefore, a precise modeling of sound durations is critical. In this paper we compare several modeling of phoneme durations (including duration modeling by HTS and MERLIN toolkits), and we propose a new approach which relies on using a set of models, each one being optimal for a given phoneme class (e.g., simple consonants, geminated consonants, short vowels, and long vowels). An objective evaluation carried out on a set of test sentences shows that the proposed approach leads to a more accurate modeling of the phoneme durations.
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.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.