Voice recognition method, device and system

Abstract

The invention discloses a voice recognition method, device and system. The method comprises the following steps: acquiring a voice instruction to be recognized, and uploading the voice instruction toa server; and controlling the target object based on a recognition result returned by the server and corresponding to the voice instruction, the recognition result being used for determining a to-be-executed instruction index of the to-be-executed serial port control instruction corresponding to the voice instruction. According to the invention, the technical problems of high software and hardwarecosts of an actual product and difficulty in adapting to a processor with limited processing capacity caused by a voice recognition mode applied to the Internet of Things in the prior art are solved.

Description

technical field [0001] The present invention relates to the field of computers, in particular to a speech recognition method, device and system. Background technique [0002] A speech recognition technology (Automatic Speech Recognition, referred to as ASR) is a technology that automatically converts a user's voice into characters that a computer can recognize. Human interaction modes based on voice recognition, such as voice dialing, voice mail, voice input, and voice control, are becoming more and more popular. [0003] With the rapid development of the Internet of Things and speech recognition technology, speech recognition technology has emerged in conjunction with multiple applications of the Internet of Things. Through voice, information transmission between people and things, and between things and things has been greatly improved. exchange efficiency. [0004] However, the speech recognition methods provided in the related art generally require a better speech reco...

AI Technical Summary

Problems solved by technology

[0004] However, the speech recognition methods provided in the related art generally require a better speech recognition training model and a supporting speech recognition algorithm, thus requiring higher processing efficiency of the processor, which in turn leads to the failure of actual products with speech recognition functions. High software and hardware costs

Especially for some processors with limited processing power, it will be difficult to directly apply voice control to physical network embedded devices due to the limitation of processor efficiency.

[0005] For the above problems, no effective solution has been proposed

Images