中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
Speech Emotion Recognition Using Cascaded Attention Network with Joint Loss for Discrimination of Confusions

文献类型:期刊论文

作者Yang Liu, Haoqin Sun, Wenbo Guan, Yuqi Xia, Zhen Zhao
刊名Machine Intelligence Research
出版日期2023
卷号20期号:4页码:595-604
ISSN号2731-538X
关键词Speech emotion recognition (SER), 3-dimensional (3D) feature, cascaded attention network (CAN), triplet loss, joint loss
DOI10.1007/s11633-022-1356-x
英文摘要Due to the complexity of emotional expression, recognizing emotions from the speech is a critical and challenging task. In most of the studies, some specific emotions are easily classified incorrectly. In this paper, we propose a new framework that integrates cascade attention mechanism and joint loss for speech emotion recognition (SER), aiming to solve feature confusions for emotions that are difficult to be classified correctly. First, we extract the mel frequency cepstrum coefficients (MFCCs), deltas, and delta-deltas from MFCCs to form 3-dimensional (3D) features, thus effectively reducing the interference of external factors. Second, we employ spatiotem poral attention to selectively discover target emotion regions from the input features, where self-attention with head fusion captures the long-range dependency of temporal features. Finally, the joint loss function is employed to distinguish emotional embeddings with high similarity to enhance the overall performance. Experiments on interactive emotional dyadic motion capture (IEMOCAP) database indicate that the method achieves a positive improvement of 2.49% and 1.13% in weighted accuracy (WA) and unweighted accuracy (UA), respectively, compared to the state-of-the-art strategies.
源URL[http://ir.ia.ac.cn/handle/173211/52352]  
专题自动化研究所_学术期刊_International Journal of Automation and Computing
作者单位School of Information Science and Technology, Qingdao University of Science and Technology, Qingdao 266061, China
推荐引用方式
GB/T 7714
Yang Liu, Haoqin Sun, Wenbo Guan, Yuqi Xia, Zhen Zhao. Speech Emotion Recognition Using Cascaded Attention Network with Joint Loss for Discrimination of Confusions[J]. Machine Intelligence Research,2023,20(4):595-604.
APA Yang Liu, Haoqin Sun, Wenbo Guan, Yuqi Xia, Zhen Zhao.(2023).Speech Emotion Recognition Using Cascaded Attention Network with Joint Loss for Discrimination of Confusions.Machine Intelligence Research,20(4),595-604.
MLA Yang Liu, Haoqin Sun, Wenbo Guan, Yuqi Xia, Zhen Zhao."Speech Emotion Recognition Using Cascaded Attention Network with Joint Loss for Discrimination of Confusions".Machine Intelligence Research 20.4(2023):595-604.

入库方式: OAI收割

来源:自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。