TTS-Portuguese Corpus: a corpus for speech synthesis in Brazilian Portuguese |
| |
Authors: | Casanova Edresson Junior Arnaldo Candido Shulby Christopher Oliveira Frederico Santos de Teixeira João Paulo Ponti Moacir Antonelli Aluísio Sandra |
| |
Affiliation: | 1.Instituto de Ciências Matemáticas e de Computa??o, University of S?o Paulo, S?o Carlos
, Brazil ;2.Federal University of Technology – Paraná (UTFPR), Medianeira, Brazil ;3.DefinedCrowd Corp.,
Seattle, USA ;4.Federal University of Mato Grosso,
Cuiabá, Brazil ;5.Research Center in Digitalization and Intelligent Robotics (CEDRI) - Instituto Politecnico de Braganca,
Bragan?a, Portugal ; |
| |
Abstract: | Speech provides a natural way for human–computer interaction. In particular, speech synthesis systems are popular in different applications, such as personal assistants, GPS applications, screen readers and accessibility tools. However, not all languages are on the same level when in terms of resources and systems for speech synthesis. 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 h 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 European Portuguese. |
| |
Keywords: | |
本文献已被 SpringerLink 等数据库收录! |
|