Facial expression robot multi-channel information emotion expression mapping method

Abstract

The present invention relates to a facial expression robot multi-channel information emotion expression mapping method comprising the steps of: pre-building an expression library, an input speech reference model, an output speech reference model and a speech output library; acquiring a to-be-identified face image, identifying emotional expressions by comparing with the expression library, acquiring a speech input, identifying voice expressions by comparing with the input speech reference model, fusing the emotional expressions and the voice expressions to obtain a composite expression instruction, and according to the composite expression instruction and by comparing with the output speech reference module, selecting corresponding speech data for output by the facial expression robot; and correspondingly setting a macro action instruction for the composite expression instruction, and performing facial expression by the facial expression robot according to the macro action instruction, thereby realizing multi-channel information emotional expression by the expression robot. By adopting the method, visual expression analysis, speech signal processing and expression robot action coordination are integrally fused to reflect visual expressions and speech emotions, so that the method has relatively high intelligence.

Description

technical field [0001] The invention relates to the field of emotion expression robots, and more specifically relates to a facial expression robot multi-channel information emotion expression mapping method. Background technique [0002] Facial expression robots are of positive significance for realizing natural human-computer interaction and reducing the emotional distance between humans and robots. Scholars at home and abroad have carried out a lot of research work on this research direction: representative expression robots include Kismet from the Artificial Intelligence Laboratory of the Massachusetts Institute of Technology, the SAYA robot developed by Tokyo Institute of Technology, and the K-bot from Hansen Robotics. And "Einstein", Nao designed by the University of Hertfordshire in the United Kingdom, ReplieeQ1, ReplieeQ2 and GeminoidTMF researched by Osaka University in Japan, H&F series robots researched by Harbin Institute of Technology in China, etc. [0003] Dif...

AI Technical Summary

Problems solved by technology

Because only one aspect of human-computer interaction is considered, and the comprehensive application of knowledge is lacking, the robot does not have the ability to express multi-channel emotions.

[0005] 2. Lack of general emotion expression modeling methods for expression robots

Therefore, in the field of domestic expression robot research, most of the research work still focuses on the mechanism design of the head, and it is obviously insufficient for how to apply intelligent technologies such as visual expression analysis and speech recognition to expression robots, especially the lack of unified universal emotion. Express Modeling Standard

Images