Duration modeling using DNN for Arabic speech synthesis - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2018

Duration modeling using DNN for Arabic speech synthesis

Abstract

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.
Fichier principal
Vignette du fichier
SP18_paper_78_version_final.pdf (239.9 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01889917 , version 1 (08-10-2018)

Identifiers

  • HAL Id : hal-01889917 , version 1

Cite

Imene Zangar, Zied Mnasri, Vincent Colotte, Denis Jouvet, Amal Houidhek. Duration modeling using DNN for Arabic speech synthesis. 9th International Conference on Speech Prosody, Jun 2018, Poznań, Poland. ⟨hal-01889917⟩
184 View
526 Download

Share

Gmail Facebook X LinkedIn More