EmoEUS: Uncertainty Supervision for Multimodal Emotion Recognition in Conversation
EmoEUS:对话中多模态情感识别的不确定性监督
机构 * Dept. of Electrical and Electronic Engineering, The Hong Kong Polytechnic University(香港理工大学电子与电气工程系) ; Speech, Language, and Cognition Laboratory, The University of Hong Kong(香港大学语音、语言与认知实验室)
AI总结 研究对话中多模态情感识别,提出EmoEUS框架,通过动态加权模态执行不确定性感知多模态融合,并引入显式监督损失,实验证明该框架优于现有方法。
Comments Accept by Interspeech 2026