Deep Temporal Interpolation of Radar-based Precipitation
Michiaki Tatsubori, Takao Moriyama, et al.
ICASSP 2022
Large speech emotion recognition datasets are hard to obtain, and small datasets may contain biases. Deep-net-based classifiers, in turn, are prone to exploit those biases and find shortcuts such as speaker characteristics. These shortcuts usually harm a model's ability to generalize. To address this challenge, we propose a gradient-based adversary learning framework that learns a speech emotion recognition task while normalizing speaker characteristics from the feature representation. We demonstrate the efficacy of our method on both speaker-independent and speaker-dependent settings and obtain new state-of-the-art results on the challenging IEMOCAP dataset.
Michiaki Tatsubori, Takao Moriyama, et al.
ICASSP 2022
Vishal Sunder, Samuel Thomas, et al.
ICASSP 2022
Xiaodong Cui, George Saon, et al.
INTERSPEECH 2023
Hagai Aronowitz
INTERSPEECH 2007