Edresson Casanova received a B.S. in computer science from the Federal University of Technology – Paraná in 2019, and a PhD in computer science and computational mathematics from the University of Sao Paulo (USP) in 2022. He is experienced in the area of speech processing, working mainly with speech synthesis, ARS, speaker verification/identification, speech-based illness identification, and resource building. Currently, he is a TTS deep learning engineer at Coqui.ai and an active open-source speech projects contributor. His research interests include multilingual speech synthesis, zero-shot multi-speaker TTS, zero-shot voice conversion, speaker verification, and ASR for low-resource languages.