Investigation of VITS Text-to-Speech for the Lithuanian Language
Vilnius University Open Series · 08.05.2026 · 140-148
DOI: 10.15388/lmitt.2026.15 ↗Kurz gefasst
Fachartikel in der Zeitschrift Vilnius University Open Series, online erschienen am 08.05.2026. Verfasst von Vytautas Lėveris und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
This study investigates the performance of the VITS model for Lithuanian speech synthesis under different training configurations. Experiments were conducted using datasets with phoneme-based and grapheme-based text representations, accented text, and both single-speaker and multi-speaker setups. The goal was to evaluate how linguistic pre-processing and speaker diversity influence synthesis quality. Model outputs were compared using objective measures. The results provide insights into the impact of phoneme representation and accent information on the quality of Lithuanian neural TTS systems.
Zitieren
APA
Lėveris, V., & Korvel, G. (2026). Investigation of VITS Text-to-Speech for the Lithuanian Language. Vilnius University Open Series, 140-148. https://doi.org/10.15388/lmitt.2026.15
Vancouver
Lėveris V, Korvel G. Investigation of VITS Text-to-Speech for the Lithuanian Language. Vilnius University Open Series. 2026:140-148. doi:10.15388/lmitt.2026.15
BibTeX
@article{Lveris2026,
author = {Lėveris, Vytautas and Korvel, Gražina},
title = {Investigation of VITS Text-to-Speech for the Lithuanian Language},
journal = {Vilnius University Open Series},
year = {2026},
pages = {140--148},
doi = {10.15388/lmitt.2026.15}
}
EUVIMED