Publications

PTL-AI Furnas Dataset: A Public Dataset for Fault Detection in Power Transmission Lines Using Aerial Images

Published in SIBGRAPI 2022, 2022

We present a new images dataset called PTL-AI Furnas Dataset as a new benchmark for fault detection in power transmission lines.

Recommended citation: Oliveira et al. "PTL-AI Furnas Dataset: A Public Dataset for Fault Detection in Power Transmission Lines Using Aerial Images." SIBGRAPI 2022 (2022). http://sibgrapi.sid.inpe.br/col/sid.inpe.br/sibgrapi/2022/09.22.22.53/doc/oliveira-33_inpe.pdf

CORAA: a large corpus of spontaneous and prepared speech manually validated for speech recognition in Brazilian Portuguese

Published in ArXiv, 2021

This paper presents CORAA (Corpus of Annotated Audios) v1. with 290.77 hours, a publicly available dataset for ASR in Brazilian Portuguese containing validated pairs (audio-transcription).

Recommended citation: Candido Junior, A., Casanova, E., Soares, A. et al. "CORAA ASR: a large corpus of spontaneous and prepared speech manually validated for speech recognition in Brazilian Portuguese." Lang Resources & Evaluation (2022). https://doi.org/10.1007/s10579-022-09621-4 https://link.springer.com/article/10.1007/s10579-022-09621-4

SC-GlowTTS: an Efficient Zero-Shot Multi-Speaker Text-To-Speech Model

Published in Interspeech, 2021

In this paper, we propose SC-GlowTTS: an efficient zero-shot multi-speaker text-to-speech model that improves similarity for speakers unseen during training.

Recommended citation: Casanova, E., Shulby, C.D., Gölge, E., Müller, N.M., Oliveira, F.S., Júnior, A.C., Soares, A.D., Aluísio, S.M., & Ponti, M.A. (2021). "SC-GlowTTS: an Efficient Zero-Shot Multi-Speaker Text-To-Speech Model". "Interspeech". https://www.isca-speech.org/archive/pdfs/interspeech_2021/casanova21b_interspeech.pdf

Brazilian Portuguese Speech Recognition Using Wav2vec 2.0

Published in International Conference on Computational Processing of the Portuguese Language., 2021

This work presents the development of an public Automatic Speech Recognition system using only open available audio data, from the fine-tuning of the Wav2vec 2.0 XLSR-53 model pre-trained in many languages over Brazilian Portuguese data.

Recommended citation: Stefanel Gris, L. R., Casanova, E., Oliveira, F. S. D., Silva Soares, A. D., & Candido Junior, A. (2022, March). "Brazilian Portuguese Speech Recognition Using Wav2vec 2.0". In International Conference on Computational Processing of the Portuguese Language (pp. 333-343). Springer, Cham. https://link.springer.com/chapter/10.1007/978-3-030-98305-5_31

TTS-Portuguese Corpus: a corpus for speech synthesis in Brazilian Portuguese

Published in Language Resources and Evaluation, 2021

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.

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

Speech2Phone: A novel and efficient method for training speaker recognition models.

Published in Brazilian Conference on Intelligent Systems, 2021

In this paper we present an efficient method for training models for speaker recognition using small or under-resourced datasets.

Recommended citation: Edresson Casanova, Arnaldo Candido Junior, Christopher Shulby, Frederico Santos de Oliveira, Lucas Rafael Stefanel Gris, Hamilton Pereira da Silva, Sandra Maria Aluísio, and Moacir Antonelli Ponti. 2021. "Speech2Phone: A Novel and Efficient Method for Training Speaker Recognition Models". In Intelligent Systems: 10th Brazilian Conference, BRACIS 2021, Virtual Event, November 29 – December 3, 2021, Proceedings, Part II. Springer-Verlag, Berlin, Heidelberg, 572–585. https://doi.org/10.1007/978-3-030-91699-2_39 https://link.springer.com/chapter/10.1007/978-3-030-91699-2_39

Discovering associative patterns in healthcare data

Published in Proceedings of Sixth International Congress on Information and Communication Technology, 2021

This study identified asymmetric associative patterns in health-related data using the Health Association Rules (HAR) algorithm.

Recommended citation: de Castro Rodrigues, D. et al. (2022). "Discovering Associative Patterns in Healthcare Data". In: Yang, XS., Sherratt, S., Dey, N., Joshi, A. (eds) Proceedings of Sixth International Congress on Information and Communication Technology. Lecture Notes in Networks and Systems, vol 235. Springer, Singapore. https://doi.org/10.1007/978-981-16-2377-6_35 https://link.springer.com/chapter/10.1007/978-981-16-2377-6_35

Fred Oliveira