Voice detection method and device, storage medium and electronic equipment

Abstract

The invention provides a voice detection method and device, a storage medium and electronic equipment, and the method comprises the steps: determining a to-be-detected voice frame signal as a suspected howling frame signal when the time domain energy and time domain harmonic content of the obtained to-be-detected voice frame signal meet a suspected howling condition; and then updating the initial reference howling frequency point according to a frequency point interval where the candidate howling frequency point in the suspected howling frame signal is located and a frequency point interval where the initial reference howling frequency point is located to obtain a target reference howling frequency point, and finally determining that the suspected howling frame signal is a howling frame signal when the target reference howling frequency point satisfies a howling condition. Primary howling detection is performed on the to-be-detected voice frame signal based on the time domain energy and the time domain harmonic content to determine the suspected howling frame signal, and secondary howling detection is performed on the suspected howling frame signal based on the target reference howling frequency point to determine the howling frame signal, so that the howling detection accuracy is effectively improved. Therefore, the technical problem that the current howling detection accuracy is low is relieved.

Description

technical field [0001] The present application relates to the field of communication technologies, and in particular, to a voice detection method, device, storage medium and electronic device. Background technique [0002] With the development of communication technology, network calls through mobile terminals have become one of the indispensable communication methods for people, so the quality of network calls becomes more and more important. [0003] During the current voice network call, the signal of the near-end receiver will be transmitted back to the near-end transmitter through the acoustic path, and then returned from the opposite end's acoustic path through the network environment to form feedback (ie howling), which seriously affects the network call quality. , in order to avoid the adverse effect of howling on the quality of network calls, it is necessary to detect and suppress howling in time. Currently, methods such as peak-to-average power ratio, peak-to-harm...

AI Technical Summary

Problems solved by technology

At present, methods such as peak-to-average power ratio, peak-to-average power ratio, and inter-frame amplitude spectrum slope deviation are usually used for howling detection. less accurate

Images