Speech enhancement method, device, equipment and storage medium

Abstract

The invention provides a voice enhancement method, device, equipment and storage medium. The method includes: acquiring a voice signal of a fixed microphone array; constructing a virtual microphone array according to the voice signal; performing phase correction on the voice signal of the fixed microphone array according to a correction factor of the virtual microphone array to obtain a virtual microphone The voice signal of the array; performing denoising processing on the voice signal of the virtual microphone array to obtain the enhanced voice signal. Therefore, without changing the physical structure of the microphone array, the attenuation of noise in different frequency bands can be flattened, high-frequency aliasing can be prevented, and the volume of the microphone array can be controlled to be small enough to be conveniently applied to portable devices.

Description

technical field [0001] The present invention relates to the technical field of speech processing, in particular to a speech enhancement method, device, equipment and storage medium. Background technique [0002] In voice intelligent interactive applications, voice enhancement technology can improve the accuracy of voice recognition and improve user experience. Therefore, voice enhancement technology is very important in both traditional voice communication and voice interactive applications. Speech enhancement technology is divided into single-channel speech enhancement technology and multi-channel speech enhancement technology. Single-channel speech enhancement technology can eliminate steady-state noise, but cannot eliminate non-stationary noise, and the increase in signal ratio is at the cost of speech damage. The more the signal-to-noise ratio is improved, the greater the speech damage. The multi-channel speech enhancement technology uses a microphone array to collect m...

AI Technical Summary

Problems solved by technology

[0003] At present, a fixed-distance microphone array is generally used to achieve speech enhancement. When a small microphone distance is set, the low-frequency noise attenuation is weak

However, if the method of increasing the microphone distance is used to enhance the attenuation of low-frequency noise, then when the microphone distance is greater than half of the highest frequency wavelength, high-frequency aliasing is prone to occur, making it difficult to eliminate high-frequency noise

[0004] In view of the above problems, the prior art uses a line array composed of multiple microphones or an area array composed of multiple microphones to overcome the problems of weak low-frequency noise attenuation and high-frequency aliasing

However, the volume of the microphone array of this method is large, which is not conducive to the application in portable devices

Images