US 12,321,382 B2
Method and apparatus for identifying music in content
Jee Hyun Park, Daejeon (KR); Jung Hyun Kim, Daejeon (KR); Hye Mi Kim, Daejeon (KR); Yong Seok Seo, Daejeon (KR); Dong Hyuck Im, Daejeon (KR); and Won Young Yoo, Daejeon (KR)
Assigned to ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE, Daejeon (KR)
Filed by ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE, Daejeon (KR)
Filed on Feb. 25, 2022, as Appl. No. 17/681,416.
Claims priority of application No. 10-2021-0157237 (KR), filed on Nov. 16, 2021.
Prior Publication US 2023/0153351 A1, May 18, 2023
Int. Cl. G06F 16/683 (2019.01); G06F 16/61 (2019.01); G10H 1/00 (2006.01)
CPC G06F 16/683 (2019.01) [G06F 16/61 (2019.01); G10H 1/0008 (2013.01); G10H 1/0041 (2013.01); G10H 2210/031 (2013.01); G10H 2240/075 (2013.01); G10H 2240/095 (2013.01); G10H 2240/135 (2013.01); G10H 2240/141 (2013.01); G10H 2250/311 (2013.01)] 14 Claims
OG exemplary drawing
 
1. A method for identifying music in a content, the method comprising:
extracting and storing a fingerprint of an original audio comprising synthesized audio in an audio fingerprint database (DB);
extracting a fingerprint of a first audio in the content; and
searching for a fingerprint corresponding to the fingerprint of the first audio in the audio fingerprint DB,
wherein the first audio is audio data in a music section detected from the content,
wherein extracting and storing the fingerprint of the original audio in the audio fingerprint DB comprises:
extracting the fingerprint of the original audio;
resynthesizing the original audio after separating a music signal and a non-music signal of the original audio, wherein the resynthesizing comprises synthesizing by amplifying the music signal and by attenuating the non-music signal; and
extracting a fingerprint of the resynthesized original audio, and
wherein the fingerprint of the original audio is mapped with the fingerprint of the resynthesized original audio in the audio fingerprint DB.