Knowledge Commons of Institute of Automation,CAS
Conversational Emotion Analysis via Attention Mechanisms | |
Zheng Lian1,3; Jianhua Tao1,2,3; Bin Liu1; Jian Huang1,3 | |
2019 | |
会议名称 | Proceedings of the 20st Annual Conference of the International Speech Communication Association (Interspeech 2019) |
会议日期 | 15-19 September, 2019 |
会议地点 | Graz, Austria |
摘要 | Different from the emotion recognition in individual utterances, we propose a multimodal learning framework using relation and dependencies among the utterances for conversational emotion analysis. The attention mechanism is applied to the fusion of the acoustic and lexical features. Then these fusion representations are fed into the self-attention based bi-directional gated recurrent unit (GRU) layer to capture long-term contextual information. To imitate real interaction patterns of different speakers, speaker embeddings are also utilized as additional inputs to distinguish the speaker identities during conversational dialogs. To verify the effectiveness of the proposed method, we conduct experiments on the IEMOCAP database. Experimental results demonstrate that our method shows absolute 2.42% performance improvement over the state-of-the-art strategies. |
收录类别 | EI |
语种 | 英语 |
七大方向——子方向分类 | 智能交互 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/44724 |
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, China 2.School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China 3.CAS Center for Excellence in Brain Science and Intelligence Technology, Beijing, China |
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. Conversational Emotion Analysis via Attention Mechanisms[C],2019. |
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 | ||
Conversational Emoti(317KB) | 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