SMIN: Semi-Supervised Multi-Modal Interaction Network for Conversational Emotion Recognition

doi:10.1109/TAFFC.2022.3141237

CORC > 自动化研究所 > 中国科学院自动化研究所 > 多模态人工智能系统全国重点实验室

	SMIN: Semi-Supervised Multi-Modal Interaction Network for Conversational Emotion Recognition
	Lian, Zheng 3,4; Liu, Bin 4; Tao, Jianhua 1,2,4
刊名	IEEE TRANSACTIONS ON AFFECTIVE COMPUTING
	2023-07-01
卷号	14 期号:3 页码:2415-2429
关键词	Emotion recognition Feature extraction Training Acoustics Semisupervised learning Benchmark testing Hidden Markov models Semi-supervised multi-modal interaction network (SMIN) conversational emotion recognition semi-supervised learning intra-modal interaction cross-modal interaction
ISSN号	1949-3045
DOI	10.1109/TAFFC.2022.3141237
通讯作者	Liu, Bin(liubin@nlpr.ia.ac.cn) ; Tao, Jianhua(jhtao@nlpr.ia.ac.cn)
英文摘要	Conversational emotion recognition is a crucial research topic in human-computer interactions. Due to the heavy annotation cost and inevitable label ambiguity, collecting large amounts of labeled data is challenging and expensive, which restricts the performance of current fully-supervised methods in this domain. To address this problem, researchers attempt to distill knowledge from unlabeled data via semi-supervised learning. However, most of these semi-supervised methods ignore multimodal interactive information, although recent works have proven that such interactive information is essential for emotion recognition. To this end, we propose a novel framework to seamlessly integrate semi-supervised learning with multimodal interactions, called "Semi-supervised Multi-modal Interaction Network (SMIN)". SMIN contains two well-designed semi-supervised modules, "Intra-modal Interactive Module (IIM)" and "Cross-modal Interactive Module (CIM)" to learn intra- and cross-modal interactions. These two modules leverage additional unlabeled data to extract emotion-salient representations. To capture additional contextual information, we utilize the hierarchical recurrent networks followed with the hybrid fusion strategy to integrate multimodal features. These multimodal features are further utilized for conversational emotion recognition. Experimental results on four benchmark datasets (i.e., IEMOCAP, MELD, CMU-MOSI and CMU-MOSEI) demonstrate that SMIN succeeds over existing state-of-the-art strategies on emotion recognition.
资助项目	National Key Research and Development Plan of China ; National Natural Science Foundation of China (NSFC)[2017YFC0820602] ; National Natural Science Foundation of China (NSFC)[61831022] ; National Natural Science Foundation of China (NSFC)[61771472] ; National Natural Science Foundation of China (NSFC)[61901473] ; [61773379]
WOS关键词	SENTIMENT ANALYSIS ; SPEECH ; FUSION
WOS研究方向	Computer Science
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:001075041900053
资助机构	National Key Research and Development Plan of China ; National Natural Science Foundation of China (NSFC)
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/52971]
专题	多模态人工智能系统全国重点实验室
通讯作者	Liu, Bin; Tao, Jianhua
作者单位	1.CAS Ctr Excellence Brain Sci & Intelligence Techno, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100190, Peoples R China 4.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Lian, Zheng,Liu, Bin,Tao, Jianhua. SMIN: Semi-Supervised Multi-Modal Interaction Network for Conversational Emotion Recognition[J]. IEEE TRANSACTIONS ON AFFECTIVE COMPUTING,2023,14(3):2415-2429.
APA	Lian, Zheng,Liu, Bin,&Tao, Jianhua.(2023).SMIN: Semi-Supervised Multi-Modal Interaction Network for Conversational Emotion Recognition.IEEE TRANSACTIONS ON AFFECTIVE COMPUTING,14(3),2415-2429.
MLA	Lian, Zheng,et al."SMIN: Semi-Supervised Multi-Modal Interaction Network for Conversational Emotion Recognition".IEEE TRANSACTIONS ON AFFECTIVE COMPUTING 14.3(2023):2415-2429.