PREVIEWING SPATIAL AUDIO SCENES COMPRISING MULTIPLE SOUND SOURCES

Patent №

US 11,368,807

Granted

2022-06-21

Filed 2020

Owner

NOKIA TECHNOLOGIES OY

Lab

AI components

3

nlp · speech · kr

Assignment

Recorded

Dataset

AIPD

2023_r1 edition

Application

17049445

An apparatus comprising means for: in response to user input, selecting at least one sound source of a spatial audio scene, comprising multiple sound sources, the spatial audio scene being defined by spatial audio content; selecting at least one related contextual sound source based on the at least one selected sound source; and causing rendering of an audio preview, representing the spatial audio content, that can be selected by a user, wherein the audio preview comprises a mix of sound sources including at least the at least one selected sound source and the at least one related contextual sound source but not all of the multiple sound sources of the spatial audio scene, and wherein selection of the audio preview causes an operation on at least the selected sound source.

Natural languageSpeechKnowledge representationH04S 7/303H04S 3/002H04S 3/008H04R 2460/07H04S 2400/01H04S 2400/11

AI classification

Speech0.95
Natural language0.67
Knowledge representation0.57
AI hardware0.10
Vision0.00
Planning0.00
Machine learning0.00
Evolutionary computation0.00

Ownership

NOKIA TECHNOLOGIES OY

assignment · 541280393

Assignors

VILERMO, MIIKKA, LEHTINIEMI, ARTO, MATE, SUJEET SHYAMSUNDAR, LAAKSONEN, LASSE

On an employer assignment, the assignors are typically the inventors.

© 2026 NYSGPT2525 LLC