DNN-Based Speech Synthesis for Arabic: Modelling and Evaluation - Archive ouverte HAL Access content directly
Conference Papers Year :

DNN-Based Speech Synthesis for Arabic: Modelling and Evaluation

(1) , (1) , (2) , (1)
1
2

Abstract

This paper investigates the use of deep neural networks (DNN) for Arabic speech synthesis. In parametric speech synthesis, whether HMM-based or DNN-based, each speech segment is described with a set of contextual features. These contextual features correspond to linguistic, phonetic and prosodic information that may affect the pronunciation of the segments. Gemination and vowel quantity (short vowel vs. long vowel) are two particular and important phenomena in Arabic language. Hence, it is worth investigating if those phenomena must be handled by using specific speech units, or if their specification in the contextual features is enough. Consequently four modelling approaches are evaluated by considering geminated consonants (respectively long vowels) either as fully-fledged phoneme units or as the same phoneme as their simple (respectively short) counterparts. Although no significant difference has been observed in previous studies relying on HMM-based modelling, this paper examines these modelling variants in the framework of DNN-based speech synthesis. Listening tests are conducted to evaluate the four modelling approaches, and to assess the performance of DNN-based Arabic speech synthesis with respect to previous HMM-based approach.
Fichier principal
Vignette du fichier
slsp-final-depose-30-juillet-2018.pdf (336.71 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01904512 , version 1 (25-10-2018)

Identifiers

  • HAL Id : hal-01904512 , version 1

Cite

Amal Houidhek, Vincent Colotte, Zied Mnasri, Denis Jouvet. DNN-Based Speech Synthesis for Arabic: Modelling and Evaluation. SLSP 2018 - 6th International Conference on Statistical Language and Speech Processing, Oct 2018, Mons, Belgium. ⟨hal-01904512⟩
149 View
426 Download

Share

Gmail Facebook Twitter LinkedIn More