Neural Text-to-Speech Synthesis for an Under-Resourced Language in a Diglossic Environment: the Case of Gascon Occitan

Ander Corral, Igor Leturia, Aure Séguier, Michäel Barret, Benaset Dazéas, Philippe Boula de Mareüil, Nicolas Quint


Abstract
Occitan is a minority language spoken in Southern France, some Alpine Valleys of Italy, and the Val d’Aran in Spain, which only very recently started developing language and speech technologies. This paper describes the first project for designing a Text-to-Speech synthesis system for one of its main regional varieties, namely Gascon. We used a state-of-the-art deep neural network approach, the Tacotron2-WaveGlow system. However, we faced two additional difficulties or challenges: on the one hand, we wanted to test if it was possible to obtain good quality results with fewer recording hours than is usually reported for such systems; on the other hand, we needed to achieve a standard, non-Occitan pronunciation of French proper names, therefore we needed to record French words and test phoneme-based approaches. The evaluation carried out over the various developed systems and approaches shows promising results with near production-ready quality. It has also allowed us to detect the phenomena for which some flaws or fall of quality occur, pointing at the direction of future work to improve the quality of the actual system and for new systems for other language varieties and voices.
Anthology ID:
2020.sltu-1.8
Volume:
Proceedings of the 1st Joint Workshop on Spoken Language Technologies for Under-resourced languages (SLTU) and Collaboration and Computing for Under-Resourced Languages (CCURL)
Month:
May
Year:
2020
Address:
Marseille, France
Venue:
SLTU
SIG:
Publisher:
European Language Resources association
Note:
Pages:
53–60
Language:
English
URL:
https://aclanthology.org/2020.sltu-1.8
DOI:
Bibkey:
Cite (ACL):
Ander Corral, Igor Leturia, Aure Séguier, Michäel Barret, Benaset Dazéas, Philippe Boula de Mareüil, and Nicolas Quint. 2020. Neural Text-to-Speech Synthesis for an Under-Resourced Language in a Diglossic Environment: the Case of Gascon Occitan. In Proceedings of the 1st Joint Workshop on Spoken Language Technologies for Under-resourced languages (SLTU) and Collaboration and Computing for Under-Resourced Languages (CCURL), pages 53–60, Marseille, France. European Language Resources association.
Cite (Informal):
Neural Text-to-Speech Synthesis for an Under-Resourced Language in a Diglossic Environment: the Case of Gascon Occitan (Corral et al., SLTU 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/remove-xml-comments/2020.sltu-1.8.pdf