US 12,731,593 B2
Method and apparatus for neural network-based audio encoding using subband decomposition
Meng Wang, Shenzhen (CN); Shan Yang, Shenzhen (CN); Qingbo Huang, Shenzhen (CN); Yuyong Kang, Shenzhen (CN); Yupeng Shi, Shenzhen (CN); Wei Xiao, Shenzhen (CN); Shidong Shang, Shenzhen (CN); and Dan Su, Shenzhen (CN)
Assigned to TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED, Shenzhen (CN)
Filed by Tencent Technology (Shenzhen) Company Limited, Shenzhen (CN)
Filed on Apr. 19, 2024, as Appl. No. 18/640,724.
Application 18/640,724 is a continuation of application No. PCT/CN2023/088638, filed on Apr. 17, 2023.
Claims priority of application No. 202210681365.X (CN), filed on Jun. 15, 2022.
Prior Publication US 2024/0265929 A1, Aug. 8, 2024
Int. Cl. G10L 19/032 (2013.01); G10L 19/02 (2013.01); G10L 21/038 (2013.01); G10L 25/30 (2013.01)
CPC G10L 19/032 (2013.01) [G10L 19/0204 (2013.01); G10L 21/038 (2013.01); G10L 25/30 (2013.01)] 20 Claims
OG exemplary drawing
 
1. An audio processing method, performed by an electronic device, comprising:
decomposing an audio signal into a low-frequency subband signal and a high-frequency subband signal;
obtaining a low-frequency feature of the low-frequency subband signal,
wherein the obtaining the low-frequency feature comprises:
performing convolution on the low-frequency subband signal to obtain a convolution feature of the low-frequency subband signal, and
performing pooling on the convolution feature to obtain a pooling feature of the low-frequency subband signal;
obtaining a high-frequency feature of the high-frequency subband signal,
wherein a feature dimensionality of the high-frequency feature is lower than a feature dimensionality of the low-frequency feature;
performing quantization encoding on the low-frequency feature to obtain a low-frequency bitstream of the audio signal; and
performing quantization encoding on the high-frequency feature to obtain a high-frequency bitstream of the audio signal.