Patent №
US 9,564,138
Granted
2017-02-07
Filed 2015
Owner
INTELLECTUAL DISCOVERY CO., LTD.
Lab
—
AI components
1
vision
Assignment
Recorded
Dataset
AIPD
2023_r1 edition
Application
14414910
The present invention relates to a method and device for encoding or decoding an object audio signal or rendering the object audio signal in a three-dimensional space. The method for processing an audio signal, according to one aspect of the present invention, comprises the steps of: generating a first object signal group and a second object signal group obtained by classifying a plurality of object signals according to a determined method; generating a first down-mix signal for the first object signal group; generating a second down-mix signal for the second object signal group; generating first object extraction information in correspondence with the first down-mix signal with respect to object signals included in the first object signal group; and generating second object extraction information in correspondence with the second down-mix signal with respect to object signals included in the second object signal group.
AI classification
Ownership
INTELLECTUAL DISCOVERY CO., LTD.
assignment · 347220903
Assignors
OH, HYUN OH, SONG, JEONGOOK, SONG, MYUNGSUK, JEON, SEWOON, LEE, TAEGYU
On an employer assignment, the assignors are typically the inventors.