projects

An interactive map of video-to-audio generation systems, metrics and datasets from 2016 to 2026

A distribution-free, unbiased and efficient evaluation metric for audio generation (ICML 2025 Workshop)

A controllable waveform-domain diffusion model for temporal-event-guided foley sound synthesis (ICASSP 2024)

A multi-instrumental FM video game music dataset with emotion annotations (ISMIR 2022)

A hand-built channel vocoder tuned to mimic the vocal sound of Daft Punk, Zedd and Stevie Wonder