【摘要】 该文在软件Agent技术基础上,提出具有识别真实人情感,同时又能够表达虚拟人个性情感的Multi-AgentSystem体系结构。在系统的感知Agent中,采用隐马尔可夫(HMM)数学模型通过表情(视觉)和语言(声音)对六种基本情感状态进行识别。实验结果说明基于视觉和听觉的多模态识别算法能提高计算机对人的情感识别率。文章最后指出面向Agent技术实现人机情感交互系统的开发是一种行之有效的方法。更多还原

【Abstract】 The system architecture for emotional interaction system based on Agent is built.In this paper the Hidden Markov Models(HMM)is used to recognize the6basic emotions from both facial expression(video)and emotional speech(audio).The findings show that the audio and video information can be combined using a rule-based system to improve the recognition rate.It is put forward that development of emotional interaction system which is realized in Agent-orient-ed technology is effective way in the last.更多还原