US 11,929,090 B2
Method and apparatus for matching audio clips, computer-readable medium, and electronic device
Fang Chao Lin, Shenzhen (CN); Wei Biao Yun, Shenzhen (CN); and Peng Zeng, Shenzhen (CN)
Assigned to TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED, Shenzhen (CN)
Filed by TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED, Guangdong (CN)
Filed on Jun. 2, 2021, as Appl. No. 17/336,562.
Application 17/336,562 is a continuation of application No. PCT/CN2020/091698, filed on May 22, 2020.
Claims priority of application No. 201910441366.5 (CN), filed on May 24, 2019.
Prior Publication US 2021/0287696 A1, Sep. 16, 2021
Int. Cl. G10L 25/54 (2013.01); G10L 25/27 (2013.01); G10L 25/51 (2013.01)
CPC G10L 25/51 (2013.01) [G10L 25/27 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method for matching audio clips, performed by a computer device, the method comprising:
obtaining a first feature sequence corresponding to a first audio clip and a second feature sequence corresponding to a second audio clip;
constructing a distance matrix between the first feature sequence and the second feature sequence, elements in the distance matrix representing respective distances between first positions in the first feature sequence and second positions in the second feature sequence;
determining a first accumulation distance between a start position and a target position in the distance matrix and a second accumulation distance between an end position and the target position in the distance matrix;
determining a minimum distance between the first feature sequence and the second feature sequence based on the first accumulation distance and the second accumulation distance; and
determining a degree of matching between the first audio clip and the second audio clip according to the minimum distance,
wherein the determining the first accumulation distance comprises:
adding an accumulation distance of a first candidate position and a distance value represented by the first candidate position in the distance matrix, to obtain a distance sum value corresponding to the first candidate position, the first candidate position being located between the start position and the target position in the distance matrix; and
determining the first accumulation distance based on the distance sum value corresponding to the first candidate position.