Speech enhancement method and device, equipment and storage medium

Abstract

The invention provides a speech enhancement method and device, equipment and a storage medium, relates to the technical field of artificial intelligence, in particular to the technical field of deep learning and speech, and can be used for audio communication scenes. The specific implementation scheme is as follows: performing sub-band decomposition processing on at least two paths of target voices to obtain amplitude spectrums and phase spectrums of the at least two paths of target voices; wherein the at least two paths of target voices comprise target mixed voices and target interference voices; according to the amplitude spectrums of the at least two paths of target voices, determining the prediction probability that the target mixed voices have target pure voices in the feature domain; and according to the prediction probability and the amplitude spectrums and the phase spectrums of the at least two paths of target voices, performing sub-band synthesis processing to obtain target pure voices in the target mixed voices. The speech enhancement effect can be improved, and a new solution thought is provided for speech enhancement.

Description

technical field [0001] The present disclosure relates to the field of artificial intelligence technology, in particular to the field of deep learning technology and voice technology, and can be used in audio communication scenarios. Background technique [0002] Speech Enhancement (SE: Speech Enhancement) technology is a classic technology in the field of audio communication. It mainly refers to the anti-interference technology for extracting pure voice from the noise background when the pure voice is interfered by noise and / or echo in the real environment. [0003] The existing speech enhancement technology has insufficient ability to suppress the noise and / or echo in the mixed speech, resulting in the inability to extract high-quality pure speech from the mixed speech, which needs to be improved urgently. Contents of the invention [0004] The present disclosure provides a speech enhancement method, device, equipment and storage medium. [0005] According to an aspect o...

AI Technical Summary

Problems solved by technology

[0003] The existing speech enhancement technology has insufficient ability to suppress the noise and / or echo in the mixed speech, resulting in the inability to extract high-quality pure speech from the mixed speech, which needs to be improved urgently

Images