TY - JOUR
AU - Liang, Zonglin
AB - 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.
TI - Emotion recognition from speech using deep learning on spectrograms
JF - Journal of Intelligent and Fuzzy Systems
DO - 10.3233/jifs-191129
DA - 2020-10-07
UR - https://www.deepdyve.com/lp/ios-press/emotion-recognition-from-speech-using-deep-learning-on-spectrograms-ZZROmXRb7f
SP - 2791
EP - 2796
VL - 39
IS - 3
DP - DeepDyve
ER -