Cross-corpus speech emotion recognition using subspace learning and domain adaption

EURASIP Journal on Audio, Speech, and Music Processing

Methodology

Tun-wen Pai¹  Maoshen Jia²  Xuan Cao²  Jiawei Ru² 

[1] Department of Computer Science and Information Engineering, National Taipei University of Technology, Taipei, Taiwan;Faculty of Information Technology, Beijing University of Technology, 100124, Beijing, China;

关键词: Speech emotion recognition;    Cross-corpus;    Subspace learning;    Domain adaption;   

DOI  :  10.1186/s13636-022-00264-5

 received in 2022-08-20, accepted in 2022-12-14,  发布年份 2022

来源: Springer

【 摘 要 】

Speech emotion recognition (SER) is a hot topic in speech signal processing. When the training data and the test data come from different corpus, their feature distributions are different, which leads to the degradation of the recognition performance. Therefore, in order to solve this problem, a cross-corpus speech emotion recognition method is proposed based on subspace learning and domain adaptation in this paper. Specifically, training set data and the test set data are used to form the source domain and target domain, respectively. Then, the Hessian matrix is introduced to obtain the subspace for the extracted features in both source and target domains. In addition, an information entropy-based domain adaption method is introduced to construct the common space. In the common space, the difference between the feature distributions in the source domain and target domain is reduced as much as possible. To evaluate the performance of the proposed method, extensive experiments are conducted on cross-corpus speech emotion recognition. Experimental results show that the proposed method achieves better performance compared with some existing subspace learning and domain adaptation methods.

【 授权许可】

CC BY   
© The Author(s) 2022

【 图 表 】

12982_2022_119_Article_IEq12.gif

Fig. 1

12982_2022_119_Article_IEq10.gif

12982_2022_119_Article_IEq9.gif

12982_2022_119_Article_IEq8.gif

Fig. 1

12982_2022_119_Article_IEq6.gif

12982_2022_119_Article_IEq4.gif

12982_2022_119_Article_IEq3.gif

12982_2022_119_Article_IEq2.gif

Fig. 6

12982_2022_119_Article_IEq1.gif

Fig. 1

Fig. 3

Fig. 2

Fig. 5

Fig. 3

Fig. 1

Fig. 2

Fig. 2

Fig. 1

Fig. 3

Fig. 3

Fig. 2

Fig. 3

Fig. 1

Fig. 1

Fig. 1

Fig. 9

Fig. 8

12864_2022_9026_Article_IEq248.gif

Fig. 1

Fig. 2

12864_2022_9026_Article_IEq246.gif

Fig. 1

42004_2022_782_Tabh_HTML.png

Fig. 5

Fig. 2

Fig. 3

Fig. 4

Fig. 5

Fig. 3

12888_2022_4137_Article_IEq1.gif

Fig. 6

Fig. 2

Fig. 2

12864_2022_9026_Article_IEq225.gif

Fig. 7

13068_2022_2229_Article_IEq2.gif

Fig. 2

Fig. 1

Fig. 1