A device, computer program and method

The client device uses a trained AI model to predict and inpaint audio gaps, addressing network-induced stuttering for a seamless gaming experience by generating predicted audio that smoothly transitions with resumed audio.

WO2025202592A1PCT designated stage Publication Date: 2025-10-02SONY GROUP CORP +1
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
PCT/GB2025/050480
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2024-03-28
Filing Date
2025-03-10
Publication Date
2025-10-02

Smart Images

  • Figure GB2025050480_02102025_PF_FP_ABST
    Figure GB2025050480_02102025_PF_FP_ABST
Patent Text Reader

Abstract

A method of audio inpainting in a client device, comprising: receiving game audio from a server; identifying a gap in the received game audio; applying the game audio to a trained artificial intelligence model to generate predicted game audio; inpainting the generated predicted game audio in the gap to generate output game audio; and outputting the output game audio.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Resolving time-delays using generative models

    US20190369946A1

  • Audio packet loss concealment via packet replication at decoder input

    US20220392459A1

  • Audio processing of missing audio information

    US20230326468A1

  • Real-time packet loss concealment using deep generative networks

    US20230377584A1