US 12,223,969 B2
Training method and device for audio separation network, audio separation method and device, and medium
Jun Wang, Shenzhen (CN); Wing Yip Lam, Shenzhen (CN); Dan Su, Shenzhen (CN); and Dong Yu, Shenzhen (CN)
Assigned to TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED, Shenzhen (CN)
Filed by TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED, Guangdong (CN)
Filed on Feb. 28, 2022, as Appl. No. 17/682,399.
Application 17/682,399 is a continuation of application No. PCT/CN2020/126492, filed on Nov. 4, 2020.
Claims priority of application No. 202010086752.X (CN), filed on Feb. 11, 2020.
Prior Publication US 2022/0180882 A1, Jun. 9, 2022
Int. Cl. G10L 19/06 (2013.01); G06N 3/045 (2023.01); G06N 3/088 (2023.01); G10L 25/30 (2013.01)
CPC G10L 19/06 (2013.01) [G06N 3/045 (2023.01); G06N 3/088 (2013.01); G10L 25/30 (2013.01)] 17 Claims
OG exemplary drawing
 
1. A method of training an audio separation network, the method comprising:
obtaining a first separation sample set, the first separation sample set comprising at least two types of audio signals with dummy labels;
obtaining a first sample set by performing interpolation on the first separation sample set based on perturbation data;
obtaining a second separation sample set by separating the first sample set using an unsupervised network;
determining losses of second separation samples in the second separation sample set; and
adjusting network parameters of the unsupervised network based on the losses of the second separation samples, such that a first loss of a first separation result outputted by an adjusted unsupervised network meets a convergence condition,
wherein the determining the losses of the second separation samples in the second separation sample set comprises obtaining a loss set by:
determining a loss between each second separation sample and true value data of the first separation sample set; and
obtaining a loss of each second separation sample, and
wherein the adjusting the network parameters of the unsupervised network based on the losses of the second separation samples comprises obtaining updated network parameters by:
determining a minimum loss from the loss set; and
updating the network parameters of the unsupervised network based on the minimum loss.