CHEAVD: a Chinese natural emotional audio–visual database

	CHEAVD: a Chinese natural emotional audio–visual database
	Ya Li; Jianhua Tao; Linlin Chao; Wei Bao; Yazhu Liu
发表期刊	Journal of Ambient Intelligence and Humanized Computing
	2016
期号	4 页码:1-12
其他摘要	This paper presents a recently collected natural, multi-modal, rich-annotated emotion database, CASIA Chinese Natural Emotional Audio-Visual Database (CHEAVD), which aims to provide a basic resource for the research on multimodal multimedia interaction. This corpus contains 140 minutes emotional segments extracted from films, TV plays and talk shows. 238 speakers, aging from child to elderly, constitute broad coverage of speaker diversity, which makes this database a valuable addition to the existing emotional databases. In total, 26 non-prototypical emotional states, including the basic six, are labeled by four native speakers. In contrast to other existing emotional databases, we provide multi-emotion labels and fake/suppressed emotion labels. To our best knowledge, this database is the first large-scale Chinese natural emotion corpus dealing with multi-modal and natural emotion, and free to research use. Automatic emotion recognition with Long Short-Term Memory Recurrent Neural Networks (LSTM-RNN) is performed on this corpus. Experiments show that an average accuracy of 56% could be achieved on six major emotion states.
关键词	Emotion Recognition
收录类别	SCI
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/40832
专题	多模态人工智能系统全国重点实验室_智能交互
推荐引用方式 GB/T 7714	Ya Li,Jianhua Tao,Linlin Chao,等. CHEAVD: a Chinese natural emotional audio–visual database[J]. Journal of Ambient Intelligence and Humanized Computing,2016(4):1-12.
APA	Ya Li,Jianhua Tao,Linlin Chao,Wei Bao,&Yazhu Liu.(2016).CHEAVD: a Chinese natural emotional audio–visual database.Journal of Ambient Intelligence and Humanized Computing(4),1-12.
MLA	Ya Li,et al."CHEAVD: a Chinese natural emotional audio–visual database".Journal of Ambient Intelligence and Humanized Computing .4(2016):1-12.