Knowledge Commons of Institute of Automation,CAS
Context-Dependent Domain Adversarial Neural Network for Multimodal Emotion Recognition | |
Zheng Lian1,3; Jianhua Tao1,2,3; Bin Liu1; Jian Huang1,3; Zhanlei Yang4; Rongjun Li4 | |
2020 | |
会议名称 | Proceedings of the 21st Annual Conference of the International Speech Communication Association (Interspeech 2020) |
会议日期 | 25-29 October, 2020 |
会议地点 | Shanghai, China |
摘要 | Emotion recognition remains a complex task due to speaker variations and low-resource training samples. To address these difficulties, we focus on the domain adversarial neural networks (DANN) for emotion recognition. The primary task is to predict emotion labels. The secondary task is to learn a common representation where speaker identities can not be distinguished. By using this approach, we bring the representations of different speakers closer. Meanwhile, through using the unlabeled data in the training process, we alleviate the impact of lowresource training samples. In the meantime, prior work found that contextual information and multimodal features are important for emotion recognition. However, previous DANN based approaches ignore these information, thus limiting their performance. In this paper, we propose the context-dependent domain adversarial neural network for multimodal emotion recognition. |
收录类别 | EI |
语种 | 英语 |
七大方向——子方向分类 | 多模态智能 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/44722 |
专题 | 多模态人工智能系统全国重点实验室_智能交互 |
作者单位 | 1.National Laboratory of Pattern Recognition, CASIA, Beijing 2.CAS Center for Excellence in Brain Science and Intelligence Technology, Beijing 3.School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 4.Huawei Technologies Co., LTD., Beijing |
第一作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Zheng Lian,Jianhua Tao,Bin Liu,et al. Context-Dependent Domain Adversarial Neural Network for Multimodal Emotion Recognition[C],2020. |
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 | ||
Context-Dependent Do(348KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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。
修改评论