Method and electronic equipment for recognizing orientation and identification

Abstract

The embodiment of the invention provides a method and electronic equipment for recognizing orientation and identification, and relates to the field of computers. The method and electronic equipment for recognizing the orientation and the identification can improve the precision of recognition on a speaker, improve the efficiency of the recognition, and achieve real-time feedback. According to the method, a first orientation collection of sound sources is obtained firstly through sound source location, a second orientation collection of the sound sources is then obtained by locating people with lip actions, an identification collection of the people with the lip actions is obtained, then a third orientation collection containing the orientation information of the speakers is obtained according to the first orientation collection and the second orientation collection, and finally the orientation and the identification of the speaker is determined according to the third orientation collection and the identification collection. The method and electronic equipment for recognizing the orientation and the identification are applied to locating of the sound sources and the recognition of the sound source identification.

Description

technical field [0001] The invention relates to the field of computers, in particular to a method and electronic equipment for identifying orientation and identity. Background technique [0002] At present, with the rapid development of speech technology, sound source localization can be applied to many fields. For example, in a scene where there are many people communicating, use appropriate technology to judge the speaker's orientation and identity; another example is in a low-cost multi-person video conference system, or on a mobile robot platform, or on a Smart On the TV, even the intelligent lighting control of the stage and so on. [0003] Taking the scene where there are many people communicating as an example, when faced with multiple input sound sources or multiple speakers, the traditional approach is: first collect the sound signal through a microphone array (Mic Array), and then use it in the array The acquired sound waves of different channels are transformed ...

AI Technical Summary

Problems solved by technology

[0004] Moreover, the actual environment is often very complicated, and various noises will have a great impact on the correct operation of the final positioning and identification, and the 10-20s sound sample collection process is too long, which also makes it impossible for the entire system to give real-time feedback

Images