TTS-Portuguese Corpus: a corpus for speech synthesis in Brazilian Portuguese
Published in Language Resources and Evaluation, 2021
Recommended citation: Casanova, E., Junior, A.C., Shulby, C. et al. "TTS-Portuguese Corpus: a corpus for speech synthesis in Brazilian Portuguese". Lang Resources & Evaluation 56, 1043–1055 (2022). https://doi.org/10.1007/s10579-021-09570-4 https://link.springer.com/article/10.1007/s10579-021-09570-4
This work consists of creating publicly available resources for Brazilian Portuguese in the form of a novel dataset along with deep learning models for end-to-end speech synthesis. Such dataset has 10.5 hours from a single speaker, from which a Tacotron 2 model with the RTISI-LA vocoder presented the best performance, achieving a 4.03 MOS value. The obtained results are comparable to related works covering English language and the state-of-the-art in Portuguese.
Bibtex:
@article{casanova2022tts, title={TTS-Portuguese Corpus: a corpus for speech synthesis in Brazilian Portuguese}, author={Casanova, Edresson and Junior, Arnaldo Candido and Shulby, Christopher and Oliveira, Frederico Santos de and Teixeira, Jo{~a}o Paulo and Ponti, Moacir Antonelli and Alu{'\i}sio, Sandra}, journal={Language Resources and Evaluation}, pages={1–13}, year={2022}, publisher={Springer} }