US 12,067,999 B2
Audio signal processing method and system for echo suppression
Jinbo Zheng, Shenzhen (CN); Meilin Zhou, Shenzhen (CN); Fengyun Liao, Shenzhen (CN); and Xin Qi, Shenzhen (CN)
Assigned to Shenzhen SHOKZ Co., Ltd., Shenzhen (CN)
Filed by Shenzhen SHOKZ Co., Ltd., Shenzhen (CN)
Filed on Aug. 9, 2021, as Appl. No. 17/397,797.
Application 17/397,797 is a continuation of application No. PCT/CN2020/140215, filed on Dec. 28, 2020.
Prior Publication US 2022/0208207 A1, Jun. 30, 2022
Int. Cl. G10L 21/0232 (2013.01); G10L 21/0208 (2013.01); G10L 21/0216 (2013.01)
CPC G10L 21/0232 (2013.01) [G10L 2021/02082 (2013.01); G10L 2021/02166 (2013.01)] 18 Claims
OG exemplary drawing
 
1. An audio signal processing system for echo suppression, comprising:
at least one non-transitory storage medium storing a set of instructions for audio signal processing for echo suppression; and
at least one processor in communication with the at least one storage medium, wherein during operation, the at least one processor executes the set of instructions to:
select, based on a speaker input signal, a target audio processing mode of an electronic device from a plurality of audio processing modes, wherein the speaker input signal includes an audio signal sent by a control device to the electronic device;
generate a target audio signal by processing a microphone signal in the target audio processing mode to reduce an echo in the target audio signal, wherein the microphone signal is an output signal of a microphone module obtained by the electronic device, and the microphone module includes at least one first-type microphone and at least one second-type microphone; and
output the target audio signal, wherein
to select the target audio processing mode of the electronic device from the plurality of audio processing modes based on the speaker input signal, the at least one processor executes the set of instructions to:
generate, based on strength of the speaker input signal, a control signal corresponding to the speaker input signal, wherein the control signal includes a first control signal or a second control signal, including:
generating the control signal based on the strength of the speaker input signal and the microphone signal, including:
 generating the control signal based on the strength of the speaker input signal and the evaluation parameter, including:
 determining that the strength of the speaker input signal is higher than a preset speaker threshold, and generating the second control signal, determining that the strength of the speaker input signal is lower than the speaker threshold and that the ambient noise evaluation parameter is beyond a preset noise evaluation range, and generating the first control signal, or determining that the strength of the speaker input signal is lower than the speaker threshold and that the ambient noise evaluation parameter is within the noise evaluation range, and generating the first control signal or the second control signal.