example cover photo

Hi! I'm Edresson Casanova,
a Ph.D. Student at the Institute of Mathematics and Computer Sciences (ICMC), University of São Paulo (USP).

Take a look at my ongoing projects and at some of my publications.
You can read more about me here.
Contact me by email.

About Me

I'm a 2st year Ph.D student in computer science at the Institute of Mathematics and Computer Sciences (ICMC), University of São Paulo (USP).

Recently, I'm a member of NILC (Interinstitutional Center for Computational Linguistics), a renowned NLP Research group in Brazil and I participate in R&D projects in Speech at CEIA (Center of Excellence in Artificial Intelligence)

I took my bachelor's degree in Computer Science at the Federal University of Technology – Paraná. I started to learn about ML and NLP for my final project, under the supervision of Arnaldo Candido Junior . As a result, I created and made available a dataset for speech synthesis in Brazilian Portuguese, and developed a Speech synthesizer (TTS) for the Brazilian Portuguese publicly available.

Projects

Open source contributions

Mozilla TTS

I implemented and made the MultiSpeaker Synthesis model available. This includes training an Encoder speaker using the Angular Prototypical loss function. Support for Global Style Token (GST) for the Tacotron 1 and Tacotron 2 models and other things.
Number of commits accepted in the repository: 42
More details

Publications

Conferences:

Journals: