Speech recognition method, device, computer equipment and readable storage medium

Abstract

The embodiment of the invention provides a voice recognition method, a voice recognition device, a computer device and a readable storage medium. The method comprises the following steps: when a microphone in a group of microphones is used, collecting voiceprint data of each microphone in the group of microphones; extracting characteristic parameters of the voiceprint data of each microphone respectively, and calculating the difference value of the voiceprint data of each two adjacent microphones according to the characteristic parameters, wherein the difference value represents the similarityof the voiceprint data of each two adjacent microphones; according to the magnitude of energy of the voiceprint data of each two adjacent microphones corresponding to the difference value which is greater than a preset value, determining the voiceprint data of the microphone which is currently used in the voiceprint data of the two adjacent microphones corresponding to the difference value whichis greater than the preset value, by adopting the voiceprint data of the microphone which is currently used as an identification text, determining the other voiceprint data except the identification text in the voiceprint data of all the microphones as a repeated recognition text, and carrying out voice recognition on the microphone which is currently used by the aid of the recognition text.

Description

technical field [0001] The invention relates to the technical field of voice recognition, in particular to a voice recognition method, device, computer equipment and a readable storage medium. Background technique [0002] With the maturity of speech recognition technology, in many cases, it is necessary to use multiple people for speech recognition. to the problem of crosstalk. Such as figure 1 As shown, a microphone group includes microphones 1, 2, 3...N. When the user speaks to a microphone 2, the adjacent microphones 1 and 3 will also receive the same but relatively small voiceprint. In addition to receiving the sound of microphone 2, the voice recognition system also received the voices of microphones 1 and 3 at the same time. However, the voices received by microphones 1 and 3 were repetitive sounds for the voice recognition system, which made the voice recognition system appear. There are a lot of repeated recognition texts. Repeated recognition texts will interfer...

AI Technical Summary

Problems solved by technology

[0003] The embodiment of the present invention provides a speech recognition method to solve the technical problem in the prior art that the recognition results are poorly readable or speech recognition cannot be performed due to the existence of repeated recognition texts during speech recognition.

[0004] The embodiment of the present invention also provides a computer device to solve the technical problem in the prior art that the recognition results are poorly readable or speech recognition cannot be performed due to the existence of repeated recognition texts during speech recognition

Images