Speech Emotion Recognition Based on Multi-Task Learning

Abstract

The complexity of emotion generation, expression, and data annotation make emotion recognition very challenging. As a kind of transfer learning, multi-task learning can aggregate multiple related corpora to achieve data sharing, and achieve the feature level sharing by utilizing the correlation of tasks, improving the training efficiency and accuracy. In this paper, we investigate the application of multi-task learning in the field of speech emotion recognition, including the model analysis, the database selection and the feature extraction. And the key research points of the research are proposed.