公开(公告)号：US20240273402A1

公开(公告)日：2024-08-15

申请号：US18169015

申请日：2023-02-14

Applicant: Sony Interactive Entertainment Inc.

Inventor： Victoria Dorn ,  Anders Lykkehoy ,  Michael Gibbes

IPC: G06N20/00

CPC classification number: G06N20/00

Abstract: A description of a reference version of an in-app asset is provided to an artificial intelligence model. A contextual communication is provided to the artificial intelligence model, wherein the contextual communication specifies a contextual feature for generation of variations of the reference version of the in-app asset. The artificial intelligence model is executed to automatically generate a variation of the in-app asset based on the contextual feature specified by the contextual communication, where the variation of the in-app asset is defined relative to the reference version of the in-app asset. The automatically generated variation of the in-app asset is conveyed for human assessment. In some embodiments, the automatically generated variation of the in-app asset is subjected to an automatic culling process before being conveyed for human assessment. In some embodiments, the in-app asset is defined by multiple layers. The in-app asset is either an audio asset or a graphical asset.

公开(公告)号：US20240261685A1

公开(公告)日：2024-08-08

申请号：US18164507

申请日：2023-02-03

Applicant: Sony Interactive Entertainment Inc.

Inventor： Victoria Dorn ,  Brandon Sangston ,  Anders Lykkehoy

IPC: A63F13/54 ,  A63F13/52 ,  A63F13/60 ,  H04S7/00

CPC classification number: A63F13/54 ,  A63F13/52 ,  A63F13/60 ,  H04S7/302 ,  H04S2400/11 ,  H04S2400/13 ,  H04S2400/15 ,  H04S2420/11

Abstract: A specification of sound producing elements within a graphical scene is provided as input to an artificial intelligence (AI) model. The specification of the sound producing elements includes a description of each sound producing element and a position of each sound producing element within a three-dimensional (3D) space relative to a virtual ambisonic microphone location within the graphical scene. A library of sound effects is also provided as input to the AI model. The AI model is executed to automatically generate an ambisonic soundfield for the specification of sound producing elements within the graphical scene from the library of sound effects. The automatically generated ambisonic soundfield is conveyed to a client computing system for post-processing by a sound designer.