Patent · US Active

Audio renderer based on audiovisual information

US11546692B1 · kind B1 · utility

1Cited by
4References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateJul 8, 2021
Grant dateJan 3, 2023
Priority date
Expiry dateJul 8, 2041

Classification

  • Technology area (CPC H)Electricity
  • CPC primaryH04S2420/11
  • WIPO fieldAudio-visual technology
  • WIPO sectorElectrical engineering

Abstract

An audio renderer can have a machine learning model that jointly processes audio and visual information of an audiovisual recording. The audio renderer can generate output audio channels. Sounds captured in the audiovisual recording and present in the output audio channels are spatially mapped based on the joint processing of the audio and visual information by the machine learning model. Other aspects are described.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.