We are Smile Lab, we are a part of JHU Center for Language and Speech Processing (CLSP).

Our lab explores how to make speech technology more natural, expressive, and trustworthy. We work on deep learning methods for speech synthesis, voice conversion, and expressive speech modeling, aiming to create systems that can capture the richness of human communication. At the same time, we care deeply about safety and develop tools for deepfake detection and anti-spoofing to help protect society in an era of powerful generative AI. We also study healthcare applications of speech and language, where technology can support accessibility.