US 11,659,325 B2
Method and system for performing voice processing
Jingran Li, Beijing (CN); and Liufeng Wang, Beijing (CN)
Assigned to BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD., Beijing (CN)
Filed by BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD., Beijing (CN)
Filed on Dec. 23, 2021, as Appl. No. 17/560,418.
Claims priority of application No. 202110195343.8 (CN), filed on Feb. 19, 2021.
Prior Publication US 2022/0272442 A1, Aug. 25, 2022
Int. Cl. H04R 1/40 (2006.01); H04R 5/04 (2006.01)
CPC H04R 1/406 (2013.01) [H04R 5/04 (2013.01); H04R 2430/20 (2013.01)] 12 Claims
OG exemplary drawing
 
1. A voice processing method, comprising:
sending a recording instruction by a first device when the first device detects that the first device opens a preset application;
collecting, by a voice processing device, a first audio signal in response to receiving the recording instruction;
processing, by the voice processing device, the first audio signal using a preset algorithm to obtain a second audio signal;
sending, by the voice processing device, the second audio signal to the first device; and
performing, by the first device, a voice processing operation on the second audio signal,
wherein the preset application comprises a recording application, a translation application, or a recognition application, and the voice processing operation comprises correspondingly a recording operation, a translation operation or a recognition operation.