Litcius/Paper detail

AudioScopeV2: Audio-Visual Attention Architectures for Calibrated Open-Domain On-Screen Sound Separation

Efthymios Tzinis, Scott Wisdom, Tal Remez, John R. Hershey

2022Lecture notes in computer science22 citationsDOI

Topics & Concepts

Computer scienceSeparation (statistics)Audio visualSurround soundSpeech recognitionArtificial intelligenceSound (geography)Machine learningMultimediaGeologyGeomorphologySpeech and Audio ProcessingMusic and Audio ProcessingHearing Loss and Rehabilitation
AudioScopeV2: Audio-Visual Attention Architectures for Calibrated Open-Domain On-Screen Sound Separation | Litcius