Adobe's TAC timestamped audio captioning model accepted at NeurIPS, hits SOTA

justin_salamon · x · 2026-09-30

Adobe Research's TAC (Timestamped Audio Captioning) has been accepted at NeurIPS 2026. The model produces timestamped captions for any audio or audiovisual source, tagging overlapping sound events with type labels ([music], [sfx], [speech]).

Original post →

More from Research

Research channel →