News
- Nov 2026 My team presented Project Sound Bender at the Adobe MAX 2026 Sneaks: describe a sound, pull it out of a finished mix, and shape it in real time on an interactive canvas. Watch the video.
- Nov 2026 Three new preprints out: FoleyForge and PromptSep-Speaker (under review at ICASSP 2027), and CrossEdit (under review at ICLR 2027).
- Oct 2026 Gave an invited talk, Sound Design AI, at the Conversational AI Reading Group at Mila. Watch the recording.
- Oct 2026 TAC: Timestamped Audio Captioning was accepted to NeurIPS 2026!
- Oct 2026 Smorph: Playable Sound Morphing with Diffusion Models will appear at ISMIR 2026 in Abu Dhabi.
- Aug 2026 Dramarrator, an object-based audio editor for audio drama production, was accepted to UIST 2026.
- Jun 2026 Keynote speaker at the +RAIN Film Festival in Barcelona, the first AI film festival in Europe.
- May 2026 AudioChat was accepted to ICML 2026!
- May 2026 Organized the MIR Happy Hour at ICASSP 2026 in Barcelona.
- Feb 2026 Five papers accepted to ICASSP 2026 in Barcelona (including Generative Audio Extension and Morphing), plus SoundStager at CHI 2026.
- Jan 2026 OpenFLAM is out: we open-sourced the code for our ICML 2025 paper FLAM: Frame-Wise Language-Audio Modeling. More in the blog post.
- Jan 2026 New blog post: Year 12,025 of the Human Era