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
会议名称ACM Multimedia 2015
会议录名称Proceedings of the 5th International Workshop on Audio/Visual Emotion Challenge
页码65-72
会议日期2015-11
会议地点Brisbane, Australia
摘要1; 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.   
关键词Multimodal
收录类别EI
语种英语
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/11848
专题模式识别国家重点实验室_语音交互
通讯作者Linlin Chao
作者单位Institute of Automation, Chinese Academy of Sciences
推荐引用方式
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.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
2015_LongShortTerm_A(1210KB)会议论文 开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Linlin Chao]的文章
[Jianhua Tao]的文章
[Minghao Yang]的文章
百度学术
百度学术中相似的文章
[Linlin Chao]的文章
[Jianhua Tao]的文章
[Minghao Yang]的文章
必应学术
必应学术中相似的文章
[Linlin Chao]的文章
[Jianhua Tao]的文章
[Minghao Yang]的文章
相关权益政策
暂无数据
收藏/分享
文件名: 2015_LongShortTerm_ACMAVEC@MM15_EI.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

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。