Echo cancellation method, device and system based on double-ended sound detection

Abstract

A method, device and system for echo cancellation based on double-end sound detection, wherein the method includes: acquiring an input sound signal from a sound collection device; performing adaptive filtering on the input sound signal to obtain a near-end speech estimation signal; Determine the current utterance state according to the near-end speech estimation signal; acquire a mapping relationship between a preset utterance state and a processing method, and obtain a processing method corresponding to the current utterance state according to the mapping relationship; according to the processing The method processes the near-end speech estimation signal; outputs the processed near-end speech estimation signal to obtain the output signal. Through this method, the echo can be better eliminated, and the duplex call experience of the hands-free voice communication terminal can be improved.

Description

technical field [0001] The present application relates to the field of voice communication, in particular to an echo cancellation method, device and system based on double talk detection. Background technique [0002] In a telephone terminal, the acoustic echo is due to the coupling between the speaker and the terminal microphone, causing the telephone's microphone to contain not only the useful speech signal but also the echo. If the microphone signal is not processed, the echo signal and the near-end voice signal will be transmitted to the far-end speaker for playback, and the far-end caller will hear his own delayed voice, which will make people feel uncomfortable and affect the call Effect. When the echo is loud, calls can't even work properly. Therefore, effective measures must be taken to suppress the echo and eliminate its influence in order to improve the quality of voice communication. [0003] For example, in teleconferencing, hands-free telephone and other syst...

AI Technical Summary

Problems solved by technology

Compared with handheld calls, the signal-to-return ratio of the microphone is usually lower during hands-free calls, and the distance between the microphone and the near-end speaker, the volume of the near-end speaker, and the size of the echo will all change the signal-to-return ratio, which makes the traditional The double-talk detection algorithm based on the fixed threshold often fails, and it is difficult to balance the duplex and echo removal performance in hands-free calls

[0008] To sum up, the echo cancellation technology in the prior art cannot accurately filter out the echo interference in the double-end sound problem, especially the double-end sound problem in the hands-free call and the conference call, and the call quality is easily affected

Images