| Full text | |
| Author(s): Show less - |
Casanova, Edresson
;
Weber, Julian
;
Shulby, Christopher
;
Candido Junior, Arnaldo
;
Goelge, Eren
;
Ponti, Moacir Antonelli
;
Chaudhuri, K
;
Jegelka, S
;
Song, L
;
Szepesvari, C
;
Niu, G
;
Sabato, S
Total Authors: 12
|
| Document type: | Journal article |
| Source: | INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 162; v. N/A, p. 12-pg., 2022-01-01. |
| Abstract | |
YourTTS brings the power of a multilingual approach to the task of zero-shot multi-speaker TTS. Our method builds upon the VITS model and adds several novel modifications for zero-shot multispeaker and multilingual training. We achieved state-of-the-art (SOTA) results in zero-shot multispeaker TTS and results comparable to SOTA in zero-shot voice conversion on the VCTK dataset. Additionally, our approach achieves promising results in a target language with a single-speaker dataset, opening possibilities for zero-shot multispeaker TTS and zero-shot voice conversion systems in low-resource languages. Finally, it is possible to fine-tune the YourTTS model with less than 1 minute of speech and achieve state-of-theart results in voice similarity and with reasonable quality. This is important to allow synthesis for speakers with a very different voice or recording characteristics from those seen during training. (AU) | |
| FAPESP's process: | 19/07316-0 - Singularity theory and its applications to differential geometry, differential equations and computer vision |
| Grantee: | Farid Tari |
| Support Opportunities: | Research Projects - Thematic Grants |