This paper introduces FLEURS-R, a speech restoration applied version of the Few-shot Learning Evaluation of Universal Representations of Speech (FLEURS) corpus. FLEURS-R maintains an N-way parallel speech corpus in 102 languages as FLEURS, with improved audio quality and fidelity by applying the speech restoration model Miipher. The aim of FLEURS-R is to advance speech technology in more languages and catalyze research including text-to-speech (TTS) and other speech generation tasks in low-resource languages. Comprehensive evaluations with the restored speech and TTS baseline models trained from the new corpus show that the new corpus obtained significantly improved speech quality while maintaining the semantic contents of the speech. The corpus is publicly released via Hugging Face.
@article{arxiv.2408.06227,
title = {FLEURS-R: A Restored Multilingual Speech Corpus for Generation Tasks},
author = {Min Ma and Yuma Koizumi and Shigeki Karita and Heiga Zen and Jason Riesa and Haruko Ishikawa and Michiel Bacchiani},
journal= {arXiv preprint arXiv:2408.06227},
year = {2024}
}