US 11,869,524 B2
Audio processing method and apparatus, computer device, and storage medium
Fasheng Chen, Shenzhen (CN)
Assigned to TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED, Shenzhen (CN)
Filed by Tencent Technology (Shenzhen) Company Limited, Shenzhen (CN)
Filed on Nov. 29, 2021, as Appl. No. 17/537,170.
Application 17/537,170 is a continuation of application No. PCT/CN2020/117317, filed on Sep. 24, 2020.
Claims priority of application No. 201911059849.5 (CN), filed on Oct. 30, 2019.
Prior Publication US 2022/0084532 A1, Mar. 17, 2022
Int. Cl. H04R 29/00 (2006.01); G10L 19/24 (2013.01); G06N 3/08 (2023.01)
CPC G10L 19/24 (2013.01) [G06N 3/08 (2013.01)] 20 Claims
OG exemplary drawing
 
1. An audio processing method, performed by a computer device, the method comprising:
acquiring first audio data, a sampling rate of the first audio data being a first sampling rate;
processing the first audio data by using a super-resolution model, to obtain an output result of the super-resolution model, the super-resolution model being a machine learning (ML) model obtained by performing deep learning (DL) training using a first audio sample as input data and a second audio sample as target data, the first audio sample being obtained by performing N times downsampling on the second audio sample, N being an integer greater than or equal to 2; and
obtaining second audio data according to the output result of the super-resolution model, a sampling rate of the second audio data being a second sampling rate, the second sampling rate being N times the first sampling rate.