Separating Invisible Sounds Toward Universal Audiovisual Scene-Aware Sound Separation
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:ID2LEUVHrecord.jsonopen to challenge →
classification
cs.CV
cs.SDeess.AS
keywords
separationsoundsinvisiblesoundvisibleaudio-visualavsa-sepscene-aware
read the original abstract
The audio-visual sound separation field assumes visible sources in videos, but this excludes invisible sounds beyond the camera's view. Current methods struggle with such sounds lacking visible cues. This paper introduces a novel "Audio-Visual Scene-Aware Separation" (AVSA-Sep) framework. It includes a semantic parser for visible and invisible sounds and a separator for scene-informed separation. AVSA-Sep successfully separates both sound types, with joint training and cross-modal alignment enhancing effectiveness.
This paper has not been read by Pith yet.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.