Audio denoising method based on scene, device, electronic equipment and storage medium

Abstract

The invention provides an audio denoising method based on a scene, a device, electronic equipment and a storage medium. The method comprises the following steps: acquiring an audio signal which is obtained through voice pickup on a conversation for a present scene; carrying out effective signal extraction processing on the audio signal so as to obtain a first effective signal with an environment voice as an effective signal, and a second effective signal with a conversation human voice as an effective signal; carrying out scene recognition based on the first effective signal so as to obtain ascene recognition effect; on the basis of a scene recognition result, selecting a denoising algorithm corresponding to the scene recognition result to carry out denoising processing on the second effective signal, thereby obtaining an output signal. According to the audio denoising method based on the scene, the device, the electronic equipment and the storage medium of the embodiment of the invention, an appropriate audio denoising scheme is specifically selected for the present scene on the basis of recognition on the present scene of the conversation, then optimal denoising effects can be achieved for conversations in various scenes to the maximum extent, and the conversation experience of users can be improved.

Description

technical field [0001] The present invention relates to the technical field of audio noise reduction, and more particularly relates to a scene-based audio noise reduction method, device, electronic equipment and storage medium. Background technique [0002] As the use of mobile terminals becomes more and more common, people always carry mobile terminals with them all the time, so they have the opportunity to use mobile terminals in various scenarios. When people use a mobile terminal to communicate with other people, the quality of the call may be affected by environmental noise. Existing audio noise reduction methods often use a general noise reduction scheme to implement noise reduction so as to improve the call experience of users in noisy environments. [0003] However, as mentioned above, users may use mobile terminals to make calls in various scenarios, and adopting a general noise reduction solution may have a certain noise reduction effect in various scenarios, but ...

AI Technical Summary

Problems solved by technology

However, there is also such a problem in

Images