Ensemble Learning With Attention-Integrated Convolutional Recurrent Neural Network for Imbalanced Speech Emotion Recognition

Abstract

This article addresses observation duplication and lack of whole picture problems for ensemble learning with the attention model integrated convolutional recurrent neural network (ACRNN) in imbalanced speech emotion recognition. Firstly, we introduce Bagging with ACRNN and the observation duplication problem. Then Redagging is devised and proved to address the observation duplication problem by generating bootstrap samples from permutations of observations. Moreover, Augagging is proposed to get oversampling learner to participate in majority voting for addressing the lack of whole picture problem. Finally, Extensive experiments on IEMOCAP and Emo-DB samples demonstrate the superiority of our proposed methods (i.e., Redagging and Augagging).