Projects

Sori is a real-time system that transforms arbitrary audio into symbolic music, with controllable trade-off between input accordance and musicality.

TokenSynth is a codec-language-model-based neural synthesizer that generates audio from MIDI with timbre conditioned by audio or text, enabling zero-shot instrument cloning and text-to-instrument synthesis.

LaFX explores creative audio effects by manipulating neural audio codec latents, producing textures and transformations that are hard to achieve in sample space.