公开(公告)号：US20240395233A1

公开(公告)日：2024-11-28

申请号：US18671577

申请日：2024-05-22

Applicant: Google LLC

Inventor： Adam Joseph Roberts ,  Jesse Hart Engel ,  Ian Stuart Simon ,  Andrea Agostinelli ,  Neil Zeghidour ,  Christopher James Donahue ,  Antoine Caillon

IPC: G10H1/00 ,  G10H1/36 ,  G10L15/06 ,  G10L15/18 ,  G10L15/183

Abstract: Training data comprising a plurality of training pairs is obtained. Each training pair comprises instrumental audio data and vocal audio data separated from audio data of a musical work of a respective plurality of musical works. For one or more training pairs of the plurality of training pairs, the vocal audio data is processed with machine-learned model(s) of a machine-learned generative audio model grouping to obtain a vocal intermediate representation for the vocal audio data. The instrumental audio data is processed with a pre-trained encoding model to obtain an instrumental intermediate representation for the instrumental audio data. A loss function is evaluated that evaluates a difference between the vocal intermediate representation and the instrumental intermediate representation. Values of parameters of a machine-learned model of the machine-learned generative audio model grouping are modified based on the loss function.