TTS-Portuguese Corpus: a corpus for speech synthesis in Brazilian Portuguese
By Edresson Casanova, Arnaldo Cândido Júnior, Christopher Dane Shulby, Frederico Santos de Oliveira, João Paulo Ramos Teixeira, Moacir Antonelli Ponti, Sandra Maria Aluísio. 2020
24 citations recorded by the source corpus.
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.
Subfields: Artificial Intelligence, Evaluation & Benchmarks, Speech & Audio
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
In Evaluation & Benchmarks
In Speech & Audio
Citations in the corpus
- Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers (2023, positive): “It was trained on a combined dataset of VCTK [19], LibriTTS [17], and TTS-Portuguese [78].”
- Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale (2023, methodology): “Here we only need a total upsampling factor of 160 instead of 256, and we adjust the upsampling factors to [5 , 4 , 4 , 2] and kernel sizes to [11 , 8 , 8 , 4] accordingly.”
- NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers (2023, methodology): “Model Comparison We choose the previous zero-shot TTS model YourTTS [45] as the baseline, with the official code and pre-trained checkpoint4, which is trained on VCTK [44], LibriTTS [46] and TTS-Portuguese [47].”
- YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone (2021, neutral): “Portuguese: TTS-Portuguese Corpus (Casanova et al., 2022), a single-speaker dataset of the Brazilian Portuguese language with around 10 hours of speech, sampled at 48KHz.”
- Generative Pre-training for Speech with Flow Matching (2023, methodology): “…et al., 2021) is a flow-based model (Kim et al., 2021) trained on multi-lingual data, including VCTK (Yamagishi et al., 2019), TTS-portugese (Casanova et al., 2022 Training To enable zero-shot speaker adaptation , fine-tuning condition y includes masked audio x m and the force-aligned phone…”