An audio signal processing method and device

Abstract

An embodiment of the invention discloses an audio signal processing method and device. The method comprises steps as follows: to-be-processed audio signals generated in a direct broadcasting process are acquired, and audio frames are extracted from the to-be-processed audio signals; a first probability, a second probability and a third probability are determined according to a transcendental audio model; the first probability is the probability that the audio frame belongs to voice, the second probability is the probability that the audio frame belongs to music, and the third is the probability that the audio frame belongs to noise; if the first probability is smaller than a first threshold or the second probability is smaller than a second threshold and the third probability is larger than a third threshold, the fact that the audio frame contains noise is determined; after the fact that the to-be-processed audio signals contain noise is determined, the audio frame belonging to noise is denoised. The method and the device can be suitable for the application scene of direct broadcasting, denoising of the audio signals is realized, and the quality of the audio signals is improved.

Description

technical field [0001] The present invention relates to the field of computer technology, in particular to an audio signal processing method and device. Background technique [0002] The network application of live broadcasting through mobile phones is gradually popularized, but there is a big difference between the audio signal in the live broadcast and the communication process. There may be singing or performances, etc., and there may also be musical accompaniment or live accompaniment. [0003] There are currently two types of audio signal noise reduction processing: [0004] 1. Communication noise reduction technology is mainly aimed at noise other than speech, and usually divides the collected audio signal into noise and speech. Then suppress the noise and preserve the voice. With this noise reduction method, sounds such as music or even singing are easily confused as noise, resulting in serious damage to music and other content while suppressing noise. Therefore, ...

AI Technical Summary

Problems solved by technology

With this noise reduction method, sounds such as music and even singing are easily confused as noise, resulting in serious damage to music and other content while suppressing noise

Therefore, singing, accompaniment, and normal ambient sounds other than the voice during the live broadcast can easily be severely damaged

[0005] 2. Music noise reduction technology can better retain music, voice and other content, but it is usually applied to the restoration of stored audio signals, such as when old turntables or tapes are re-edited or digitized, due to the aging of the medium itself and the technology at that time Limitation, the data obtained after digitization has floor noise or background noise

However, it is difficult for the environment of mobile live broadcast to meet the high requirements of professional recording rooms, because the live broadcast venue is not limited to a quiet environment, such as: cars, restaurants, shopping malls and other noisy environments may become places for anchors to conduct live broadcasts

Images