Hi! I’m Mateo Cámara, PhD in Artificial Intelligence from the Universidad Politécnica de Madrid. My work focuses on developing audio synthesis models that combine deep learning with physical models of the vocal tract. I am particularly interested in making AI-generated sound more aligned with human speech, integrating articulatory knowledge and techniques from speech processing and acoustics. My goal is to develop more controllable and interpretable systems that go beyond traditional synthesis, unlocking new possibilities for human-computer interaction and more natural, expressive speech technologies.
Beyond my research career, I co-founded a startup, where I gained hands-on experience in transforming technology into real-world products. This journey expanded my knowledge in data science, application development, and project management.
I am passionate about the intersection of AI and human communication, continuously exploring ways to bring computation closer to how we express ourselves.
Keep reading? Have a nice day!