Learning to Separate Object Sounds by Watching Unlabeled Video
This addresses the challenge of perceiving multi-object scenes by enabling better audio source separation for applications in multimedia and robotics, though it builds on existing multi-instance learning frameworks.
The paper tackles the problem of separating mixed audio sources in videos by learning audio-visual object models from unlabeled video, using visual context to guide separation. It achieves state-of-the-art results in audio source separation and denoising, as demonstrated on large-scale 'in the wild' videos.
Perceiving a scene most fully requires all the senses. Yet modeling how objects look and sound is challenging: most natural scenes and events contain multiple objects, and the audio track mixes all the sound sources together. We propose to learn audio-visual object models from unlabeled video, then exploit the visual context to perform audio source separation in novel videos. Our approach relies on a deep multi-instance multi-label learning framework to disentangle the audio frequency bases that map to individual visual objects, even without observing/hearing those objects in isolation. We show how the recovered disentangled bases can be used to guide audio source separation to obtain better-separated, object-level sounds. Our work is the first to learn audio source separation from large-scale "in the wild" videos containing multiple audio sources per video. We obtain state-of-the-art results on visually-aided audio source separation and audio denoising. Our video results: http://vision.cs.utexas.edu/projects/separating_object_sounds/