Showing cs.SDShow all
2 papers · 1 filter
cs.SD2026
Reference-Driven Multi-Speaker Audio Scene Generation from In-the-Wild Priors
Michael Finkelson, Daniel Segal, Eitan Richardson +7
Existing multi-speaker dialogue systems bind speakers to utterances through structured supervision: per-turn tags, multi-stream transcriptions, or learnable speaker embeddings. The…
cs.SD2025
CAFA: a Controllable Automatic Foley Artist
Roi Benita, Michael Finkelson, Tavi Halperin +2
Foley is a key element in video production, refers to the process of adding an audio signal to a silent video while ensuring semantic and temporal alignment. In recent years, the r…