상세정보
학술대회
Background Music Separation for Multichannel Audio Based on Inter-Channel Level Vector Sum
- 발행일
- 201406
- 출처
- International Symposium on Consumer Electronics (ISCE) 2014, pp.1-2
- 협약과제
- 14PR2100, UHDTV용 사운드 바를 위한 파면음 장합성 및 초점음원 기술을 이용하는 멀티채널 서라운드 프로세싱 디지털 앰프 SoC 개발, 서정일
- 초록
- In this paper, a Blind Source Separation (BSS) algorithm for multichannel audio contents is proposed. Unlike common BSS algorithms targeting stereo audio contents or microphone array signals, our technique is targeted at multichannel audio such as 5.1 and 7.1 ch audio. Since most multichannel audio object sources are panned using the Interchannel Level Difference (ILD), we employ the ILVS (Interchannel Level Vector Sum) concept to cluster common signals (such as background music) from each channel. Our proposed method can therefore separate a common audio signal from multiple channels with a lower computational complexity. Our multichannel audio content separation technique can be applied to an upmix system or a cinema audio system requiring multichannel audio source separation. © 2014 IEEE.
- KSP 제안 키워드
- Audio signal, Background music, Blind source separation(BSS), Level difference, Lower computational complexity, Multichannel audio source separation, Multiple channels, Music separation, Stereo audio, Vector sum, array signal