Double voice recognition method of service robot with independent microphone arrays

Abstract

The invention relates to a double voice recognition method of a service robot with independent microphone arrays. The double voice recognition method is characterized in that two sets of independent voice recognition systems respectively containing a microphone array are installed on a body of the service robot, one set comprises an annular microphone array and an off-line voice recognition system and is used for recognizing off-line voice texts such as daily conversations, command words and smart home control instructions, and the other set comprises a linear microphone array and an online voice recognition system and is used for performing voice recognition on the aspects of all application contents except for the off-line voice texts, the artificial brain and the like. The relation of the two sets of voice recognition systems lies in that no man-machine interaction is performed when a text acquired through voice recognition of the microphone array and the online voice recognition system is matched with an off-line voice text library, and only the content of an instruction text is sent to the microphone array and the off-line voice recognition system to act as supplementary information for the voice recognition content.

Description

technical field [0001] The invention relates to a dual voice recognition method for a service robot with an independent microphone array. It is characterized by installing two sets of independent voice recognition systems each containing a microphone array on the body of the service robot, one of which is a ring microphone array + offline voice recognition system, which is used to recognize offline conversations, command words, smart home control commands, etc. Speech text, another set of linear microphone array + online speech recognition system, used for speech recognition of all application content, free dialogue and other aspects except offline speech text. The connection between the two speech recognition systems is that when the text obtained by the microphone array + online speech recognition system through speech recognition matches the offline speech text database, no human-computer interaction is performed, and only the content of the instruction text is sent to the ...

AI Technical Summary

Problems solved by technology

[0005] At present, a set of voice recognition system is generally used on the service robot body, and it is mainly based on online voice recognition, which requires a good network environment support. If the service robot has a network connection failure or the bandwidth of the online voice cloud outlet is affected, voice will appear. Identify system failures and delays that affect the effect of human-computer interaction

Although some speech recognition solution companies are aware of this problem and have assisted the offline recognition function, that is, when the online speech recognition cannot provide online speech cloud recognition services, they switch to the offline speech recognition mode, but because the offline speech recognition is not optimized according to the scene , the effect of offline recognition is poor. This solution of only one speech recognition system at the same time online and then offline does not meet the actual needs well, and a more suitable combination of online speech recognition and offline speech recognition is needed.

Images