CASIA OpenIR  > 模式识别国家重点实验室  > 语音交互
Long Short Term Memory Recurrent Neural Network based Multimodal Dimensional Emotion Recognition
Linlin Chao; Jianhua Tao; Minghao Yang; Ya Li; Zhengqi Wen
2015
Conference NameACM Multimedia 2015
Source PublicationProceedings of the 5th International Workshop on Audio/Visual Emotion Challenge
Pages65-72
Conference Date2015-11
Conference PlaceBrisbane, Australia
Abstract1; This paper presents our effort to the Audio/Visual+ Emotion Challenge (AV+EC2015), whose goal is to predict the continuous values of the emotion dimensions arousal and valence from audio, visual and physiology based modalities. The state of art classifier for dimensional recognition, long short term memory recurrent neural network (LSTM-RNN) is utilized. Except regular LSTM-RNN prediction architecture, two techniques are investigated for dimensional emotion recognition problem. The first one isε-insensitive loss is utilized as the loss function to optimize. Compared to squared loss function, which is the most popular loss function for dimension emotion recognition,  ε-insensitive loss is more robust for the label noises. The other one is temporal pooling among successive frames. This technique enables temporal modeling in the input features and increases the diversity of the features fed into prediction architectures. Experiments results show the efficiency of each key point of the proposed method and competitive results are obtained.   
KeywordMultimodal
Indexed ByEI
Language英语
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/11848
Collection模式识别国家重点实验室_语音交互
Corresponding AuthorLinlin Chao
AffiliationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Linlin Chao,Jianhua Tao,Minghao Yang,et al. Long Short Term Memory Recurrent Neural Network based Multimodal Dimensional Emotion Recognition[C],2015:65-72.
Files in This Item: Download All
File Name/Size DocType Version Access License
2015_LongShortTerm_A(1210KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Linlin Chao]'s Articles
[Jianhua Tao]'s Articles
[Minghao Yang]'s Articles
Baidu academic
Similar articles in Baidu academic
[Linlin Chao]'s Articles
[Jianhua Tao]'s Articles
[Minghao Yang]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Linlin Chao]'s Articles
[Jianhua Tao]'s Articles
[Minghao Yang]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 2015_LongShortTerm_ACMAVEC@MM15_EI.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.