Manuel Cherep

Graduate Student

Contrastive Learning from Synthetic Audio Doppelgängers

Learning robust audio representations currently demands extensive datasets of real-world sound recordings. By applying artificial transfor…

Neural audio synthesis methods now allow specifying ideas in natural language. However, these methods produce results that cannot be easily…

Organology: Real-Time Biometrics x Sound Synthesis October 19th @ 8:00 PMMIT Media Lab 3rd Floor AtriumWhat role does the body pl…