DAn Ellis
@dpwe.bsky.social
22 followers 42 following 1 posts
Research Scientist at Google DeepMind: Enivironmental sound understanding
Posts Media Videos Starter Packs
dpwe.bsky.social
🔊New paper! Recomposer allows editing sound events within complex scenes based on textual descriptions and event roll representations. And we discuss the details that matter!

Work by the Sound Understanding folks
@GoogleDeepMind

arxiv.org/abs/2509.05256
Recomposer: Event-roll-guided generative audio editing
Editing complex real-world sound scenes is difficult because individual sound sources overlap in time. Generative models can fill-in missing or corrupted details based on their strong prior understand...
arxiv.org