Speech processing method, device, electronic device and storage medium

Abstract

The present disclosure provides a voice control method, device, electronic equipment, and storage medium. The voice control method includes: detecting the working state of the current communication system; when the working state is a double-end talking state or a remote speaking state, performing compression processing on the subsequent far-end voice signal; obtaining the near-end voice signal through the microphone; performing echo processing according to the near-end voice signal and the compressed far-end voice signal, and obtaining the echo-processed near-end voice signal and residual echo signal; Perform nonlinear suppression processing on the near-end speech signal and the residual echo signal; perform gain control on the suppressed near-end speech signal. In this embodiment, when the working state is the double-end speech state or the remote-end speech state, the received subsequent far-end voice signal is compressed, and the playback volume of the larger far-end signal is reduced, so that the echo sound collected by the microphone The amount becomes smaller, which reduces the interference of the echo, effectively suppresses the residual echo, and improves the call quality.

Description

technical field [0001] The present disclosure relates to the technical field of communications, and in particular, to a voice processing method, device, electronic equipment, and storage medium. Background technique [0002] The echo is caused by the acoustic loop between the speaker and the microphone. That is to say, the sound signal from the far end is emitted through the near-end speaker, collected by the microphone and transmitted back to the far end. At this time, the far-end speaker can hear his own echo. Thereby seriously affecting the call quality. [0003] In order to improve call quality, in the related art, an adaptive filter in an echo cancellation system can be used to simulate a feedback loop formed by an echo to cancel part of the echo signal collected by a microphone. Since the adaptive filter cannot completely eliminate the echo, especially the nonlinearly distorted echo signal, the echo signal processed by the adaptive filter is then passed through a non...

AI Technical Summary

Problems solved by technology

[0006] In order to overcome the problems existing in the related technology, the present disclosure provides a voice processing method, device, electronic equipment and storage medium to solve the technical problem that the residual echo cannot be effectively suppressed in the dual-talk state, resulting in poor call quality

Images