FLEURS-R: A Restored Multilingual Speech Corpus for Generation Tasks
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913465974652928 |
|---|---|
| author | Ma, Min Koizumi, Yuma Karita, Shigeki Zen, Heiga Riesa, Jason Ishikawa, Haruko Bacchiani, Michiel |
| author_facet | Ma, Min Koizumi, Yuma Karita, Shigeki Zen, Heiga Riesa, Jason Ishikawa, Haruko Bacchiani, Michiel |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_06227 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | FLEURS-R: A Restored Multilingual Speech Corpus for Generation Tasks Ma, Min Koizumi, Yuma Karita, Shigeki Zen, Heiga Riesa, Jason Ishikawa, Haruko Bacchiani, Michiel Computation and Language Artificial Intelligence Sound Audio and Speech Processing 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. |
| title | FLEURS-R: A Restored Multilingual Speech Corpus for Generation Tasks |
| topic | Computation and Language Artificial Intelligence Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2408.06227 |