There is a large amount of public available labeled image-based facial expression recognition datasets. How could these images help for the audio emotion recognition with limited labeled data according to their inherent correlations can be a meaningful and challenging task. In this paper, we propose a semi-supervised adversarial network that allows the knowledge transfer from the labeled videos to the heterogeneous labeled audio domain hence enhancing the audio emotion recognition performance. Specifically, face image samples are translated to the spectrograms class-wisely. To harness the translated samples in a sparsely distributed area and construct a tighter decision boundary, we propose to precisely estimate the density on feature space and incorporate the reliable low-density sample with an annealing scheme. Moreover, the unlabeled audios are collected with the high-density path in a graph representation. As a possible "recognition via generation" framework, we empirically demonstrated its effectiveness on several audio emotional recognition benchmarks.
|Title of host publication||Proc. of IEEE CVPR'2020 Workshop|
|Publisher||IEEE Computer Society|
|Publication status||Published - Jul 2020|
|Event||2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) - Seattle, WA, United States|
Duration: 14 Jun 2020 → 19 Jun 2020
|Competition||2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)|
|Period||14/06/20 → 19/06/20|