Pedro Leite

Pedro Leite is a seasoned AI researcher and software engineer with a strong background in signal processing, artificial intelligence, and software development. He holds a Master's degree in the field of Deep Learning & Signal Processing from the Federal University of Rio de Janeiro (UFRJ), where he also earned a Bachelor's degree in Software Engineering & Electronics with Cum Laude honors. Pedro has a wealth of experience in developing cutting-edge AI solutions, particularly in the fields of text-to-speech (TTS) and voice conversion technologies, which he has applied extensively in Brazilian Portuguese. Currently, Pedro works as an Innovation Researcher and AI/ML Engineer at Globo, where he develops and creates speech processing systems and AI models. Notably, he developed the first TTS workflow for large-scale audio descriptions in broadcast TV, enhancing accessibility for visually impaired audiences. His academic research includes contributions to sound source separation through deep learning and the development of open-source TTS projects. Pedro has published several articles on TTS technologies and has received awards for his work in AI-driven accessibility content for television. He is passionate about speech, audio, music, AI, and competitive gaming, and continues to advance in the field as a PhD candidate at COPPE/UFRJ.