Abstract: In response to the urgent need to realize computer-assisted automatic depression recognition, a major depressive disorder recognition study based on facial behavior and speech features for the Chinese population has been carried out. First, 72 samples conforming to the research conditions are selected from the constructed depression data set for analysis. Then, the facial activity and speech data are decomposed into different frequency components by using the variational modal decomposition method, and the feature set is constructed by analyzing the energy distribution of different frequency bands. Finally, depression recognition is achieved by using the voting decisions of several classifiers. The experimental results show that the recognition accuracy of the male group can reach 81.1% , and the recognition accuracy of the female group can reach 78.7% . Under the premise of protecting the privacy of the subjects, higher
classification results are obtained.

Key words: depression recognition , multimodal fusion , facial behavior , speech signal , variational mode decomposition