ETRI-Knowledge Sharing Plaform

ENGLISH

성과물

논문 검색
구분 SCI
연도 ~ 키워드

상세정보

학술대회 Multi-level Stereo Attention Model for Center Channel Extraction
Cited 1 time in scopus Download 1 time Share share facebook twitter linkedin kakaostory
저자
임우택, 백승권, 이태진
발행일
201906
출처
International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB) 2019, pp.1-4
DOI
https://dx.doi.org/10.1109/BMSB47279.2019.8971885
협약과제
18HS1700, 다중소스 데이터 지능형 분석기반 고수준 정보추출 원천기술 연구, 유장희
초록
In recent years, the spatial audio reproduction of digital media has become popular. Despite the demand for such spatial audio content, very little content is produced with multi-channel audio. Moreover, it is difficult to provide interactive services to users owing to the lack of object-based content. In this paper, we propose a center channel extraction method based on a multi-level convolutional neural network structure to generate object-based content. In addition, we present a novel stereo attention model which considers each channel's characteristics. By applying the proposed method to stereo audio content, we achieve better extraction performance than existing commercial application.
키워드
artificial intelligence in media processing, audio signal processing, center channel extraction, deep learning, immersive audio, source separation
KSP 제안 키워드
Attention model, Audio signal processing, Commercial application, Convolution neural network(CNN), Digital Media, Extraction method, Interactive services, Multi-level, Multichannel audio, Neural network structure, Object-based