US 11,875,808 B2
Voice call method and apparatus, electronic device, and computer-readable storage medium
Yuepeng Li, Shenzhen (CN); Zhipeng Liu, Shenzhen (CN); and Rui Zhu, Shenzhen (CN)
Assigned to TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED, Shenzhen (CN)
Filed by TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED, Shenzhen (CN)
Filed on Aug. 27, 2021, as Appl. No. 17/460,160.
Application 17/460,160 is a continuation of application No. PCT/CN2020/081385, filed on Mar. 26, 2020.
Claims priority of application No. 201910906728.3 (CN), filed on Sep. 24, 2019.
Prior Publication US 2021/0390969 A1, Dec. 16, 2021
Int. Cl. G10L 21/02 (2013.01); G10L 25/51 (2013.01); H04M 3/00 (2006.01)
CPC G10L 21/02 (2013.01) [G10L 25/51 (2013.01); H04M 3/002 (2013.01)] 13 Claims
OG exemplary drawing
 
1. A voice call method, comprising:
obtaining a voice call state of a terminal system at a historical moment, the terminal system being provided with at least two audio acquisition devices;
obtaining first voice signals acquired by the at least two audio acquisition devices at a current moment, and determining signal energy of the first voice signals; and
determining a target audio acquisition device at the current moment from the at least two audio acquisition devices based on the voice call state at the historical moment and the signal energy of the first voice signals, comprising: determining that the voice call state at the historical moment is far-end single talk:
determining an audio acquisition device corresponding to a first voice signal with the lowest signal energy as the target audio acquisition device at the current moment;
determining a quantity of times that the voice call state before the current moment is consecutively the far-end single talk; and
determining the target audio acquisition device at the current moment as the target audio acquisition device after the current moment in response to the quantity of times being greater than a specified value.