Method for cooperative voice command recognition and related system

Abstract

A method of recognizing voice commands cooperatively includes generating a voice command from a user specifying a target machine and a desired action to be performed by the target machine, and a plurality of machines receiving the voice command, the plurality of machines comprising the target machine and at least one member machine. The method also includes each of the plurality of machines performing a recognition process on the voice command to produce a corresponding recognition result, each member machine sending its corresponding recognition result to the target machine, and the target machine evaluating its own recognition result together with the recognition result from each member machine to determine a most likely final recognition result for the voice command.

Description

technical field [0001] The present invention provides a speech recognition method and a related system, especially a cooperative speech recognition method and a related system. Background technique [0002] Speech recognition technology is mainly used in communications and computers. Speech recognition (or language recognition) technology is used to recognize the sound of human language and convert it into a digital signal so that it can be input to a computer for subsequent processing. In practical applications, the voice command system can recognize hundreds of words to execute corresponding commands, so that the complicated operations caused by using a keyboard or mouse can be avoided. Common applications include discrete dictation systems. Discrete dictation systems require the speaker to pause between each word for recognition. Although continuous recognition can be used to perform speech recognition at normal speaking speeds, it requires a considerable amount of proce...

AI Technical Summary

Problems solved by technology

However, when using these devices, most users will face the problem of low accuracy of speech recognition. In many cases, the accuracy of speech recognition may be lower than 50%. Even with some practical experimental methods, The accuracy of speech recognition can be increased to about 80%. However, these experimental methods can only achieve the improvement of speech recognition accuracy after a large number of complex calculation processes, which usually limits the application of speech recognition devices.

[0005] It is not easy to achieve a simplification of the design of the automatic control device and a high accuracy of speech recognition at the same time, and since most automatic control devices are independent devices, in order to improve the accuracy of speech recognition, the automatic control device usually needs to have a More computing resources are needed to perform complex recognition algorithms, but as we can see above, this method is not practical

Images