Affiliations: Electronic Information Engineering, Changchun University of Science and Technology, Changchun, China
Correspondence:
[*]
Corresponding author. Xingguang Li, Electronic Information Engineering, Changchun University of Science and Technology, No. 7089 Satellite road, Changchun, China. E-mail: [email protected].
Abstract: In speech emotion recognition, most emotional corpora generally have problems such as inconsistent sample length and imbalance of sample categories. Considering these problems, in this paper, a variable length input CRNN deep learning model based on Focal Loss is proposed for speech emotion recognition of anger, happiness, neutrality and sadness in IEMOCAP emotional corpus. In this model, Firstly, a variable-length strategy is introduced to input the speech spectra of the filled speech samples into CNN. Then the effective part of the input sequence is preserved and output by masking matrix and convolution layer. Thirdly, the effective output of input sequence is input into BiGRU network for learning. Finally, the focal loss is used for network training to control and adjust the contribution of various samples to the total loss. Compared with the traditional speech emotion recognition model, simulations show that our method can effectively improve the accuracy and performance of emotion recognition.
Keywords: Speech emotion recognition, spectrograms, CRNN, focal loss
