Microphone abnormality detection method, device and storage medium

Abstract

The invention discloses a microphone abnormality detection method, device and storage medium, belonging to the technical field of terminals. The method includes: playing the source audio used for testing the abnormal microphone, and determining the test audio collected by the target microphone based on the source audio, and then according to the similarity between the frequency domain feature vector of the test audio and the frequency domain feature vector of the source audio, to determine whether the target microphone is an abnormal microphone. That is, in the embodiment of the present invention, abnormality detection can be performed on the target microphone alone, instead of combining test audio collected by other microphones to determine whether the target microphone is an abnormal microphone. In this way, the situation in the related art that when more than two microphones are abnormal microphones is detected incorrectly can be avoided, thereby improving the accuracy of detecting abnormal microphones.

Description

technical field [0001] The present invention relates to the field of terminal technology, in particular to a microphone abnormality detection method, device and storage medium. Background technique [0002] In order to ensure the security of the target area, the target area can be monitored based on IPC (Internet Protocol Camera, network camera). Among them, multiple microphones are deployed in the IPC, and the multiple microphones form a microphone array. During the process of monitoring the target area by the IPC, each microphone in the microphone array collects audio. According to the audio collected by each microphone in the microphone array, it can be identified Audio from the source. If one of the microphones in the microphone array is abnormal, it will affect the accuracy of identifying the audio from the sound source. Therefore, it is necessary to perform anomaly detection on each microphone in the microphone array. [0003] In the related art, when it is necessary...

AI Technical Summary

Problems solved by technology

For example, microphone A and microphone B are abnormal microphones, and microphone C is a normal microphone. At this time, the difference between the audio collected by microphone A and the audio collected by microphone C will be greater than the threshold, and the audio collected by microphone B will be different from that collected by microphone C. The difference between the audio will also be greater than the threshold. In this case, if the microphone abnormality detection is still performed according to the above method, it will be determined that microphone C is an abnormal microphone, but in fact microphone A and microphone B are abnormal microphones, and microphone C is Normal microphone, obviously, in this case, the abnormal microphone determined according to the above method is wrong

Images