Answers are grounded in this paper and cite their sources.
Speech emotion recognition is still challenging due to the complexity of emotion. Most of the current research is based on the enough data, and the training data and test data are from the same corpus. Obviously, this is not in line with the actual application scene. In addition, the emotion annotation of large amounts speech data is also a challenging task. This paper investigates and summarizes the concepts and categories, methods and applications of transfer learning briefly, and studies the combination of transfer learning and deep learning, and the application of speech emotion recognition, and then points out the key issues that need to be further solved in the research.
No takes yet. Share an insight, caveat, or question.
Han et al. (2019) studied this question.