TTS-Portuguese Corpus: a corpus for speech synthesis in Brazilian Portuguese
This provides publicly available resources for Brazilian Portuguese speech synthesis, addressing a gap for applications like accessibility tools, though it is incremental as it adapts existing methods to a new language.
The authors tackled the lack of resources for speech synthesis in Brazilian Portuguese by creating a novel 10.5-hour single-speaker dataset and deep learning models, achieving a 4.03 MOS score comparable to state-of-the-art results in English and Portuguese.
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 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.