Self-adaptive denoising method and system based on sub-band noise analysis

Abstract

The invention relates to the field of voice technologies, in particular to a self-adaptive denoising method based on sub-band noise analysis. The method includes the steps that firstly, framing and short time frequency domain transformation are conducted on input time domain audio signals with noise, and then frequency domain audio signals with noise are generated; secondly, a noise energy spectrum of the frequency domain audio signals with noise is estimated through a minimum value tracking method; thirdly, the posterior signal to noise ratio and the prior signal to noise ratio of the noise energy spectrum are calculated; fourthly, through a nonlinear gain extension method, denoising gains of all time frequency units are calculated through the posterior signal to noise ratio and the prior signal to noise ratio; fifthly, smoothing filtering is conducted on the denoising gains of all the time frequency units to reduce tone quality distortion; sixthly, the denoising gains act on all the time frequency units of the audio signals with noise in the first step, and then denoised frequency domain audio signals are acquired; seventhly, short time frequency domain inverse transformation is conducted, and then the final denoised time frequency audio signals are acquired and output. According to the method and system, stable noise in target signals can be greatly lowered.

Description

technical field [0001] The invention relates to the field of speech technology, in particular to an adaptive noise reduction method and system based on sub-band noise analysis. Background technique [0002] In the field of voice communication and recording, background noise is the biggest obstacle affecting sound quality and intelligibility. When video chatting with relatives and friends through the Internet, there will be the "hum" sound of the computer; when recording lectures, there will be the sound of writing and students chatting; when doing interviews outdoors, there will be road traffic noise and wind noise, etc. We cannot live without it in our daily life. Turn off the noise. [0003] In order to improve the sound quality, signal-to-noise ratio, and intelligibility of collected sound signals, many noise reduction algorithms have been developed internationally, which can be divided into two categories. One is to spatially select the target sound source through mult...

AI Technical Summary

Problems solved by technology

[0005] The above three types of noise reduction methods all have corresponding noise reduction effects, but they all have defects.

The first type of noise reduction method can only be applied to scenarios where the noise energy is significantly smaller than the signal energy, and the speech signal with less energy will be mistaken for noise and therefore be attenuated

The effect of the second type of noise reduction method is better than that of the first type, but there is obvious musical noise in the noise section (Musical noise)

The third type of noise reduction algorithm is more complicated than the first two types, but the adaptive filter method will affect the output sound quality due to the convergence relationship, that is to say, the faster the convergence speed will improve the noise reduction effect, but at the same time it will reduce the sound quality, and it will also affect the output sound quality. Risk of filter divergence

Images