Self-supervised Audio Spatialization with Correspondence Classifier
ICIP, pp. 3347-3351, 2019.
The audio spatialzation network consists of a spatial audio synthesizer, which predicts the left and right ideal ratio mask given visual and audio features, and a correspondence classifier, which provide auxiliary training signal to improve the performance
Spatial audio is an essential medium to audiences for 3D visual and auditory experience. However, the recording devices and techniques are expensive or inaccessible to the general public. In this work, we propose a self-supervised audio spatialization network that can generate spatial audio given the corresponding video and monaural aud...More
PPT (Upload PPT)