TY - GEN
T1 - Singing-voice separation from monaural recordings using robust principal component analysis
AU - Huang, Po Sen
AU - Chen, Scott Deeann
AU - Smaragdis, Paris
AU - Hasegawa-Johnson, Mark
PY - 2012
Y1 - 2012
N2 - Separating singing voices from music accompaniment is an important task in many applications, such as music information retrieval, lyric recognition and alignment. Music accompaniment can be assumed to be in a low-rank subspace, because of its repetition structure; on the other hand, singing voices can be regarded as relatively sparse within songs. In this paper, based on this assumption, we propose using robust principal component analysis for singing-voice separation from music accompaniment. Moreover, we examine the separation result by using a binary time-frequency masking method. Evaluations on the MIR-1K dataset show that this method can achieve around 1∼1.4 dB higher GNSDR compared with two state-of-the-art approaches without using prior training or requiring particular features.
AB - Separating singing voices from music accompaniment is an important task in many applications, such as music information retrieval, lyric recognition and alignment. Music accompaniment can be assumed to be in a low-rank subspace, because of its repetition structure; on the other hand, singing voices can be regarded as relatively sparse within songs. In this paper, based on this assumption, we propose using robust principal component analysis for singing-voice separation from music accompaniment. Moreover, we examine the separation result by using a binary time-frequency masking method. Evaluations on the MIR-1K dataset show that this method can achieve around 1∼1.4 dB higher GNSDR compared with two state-of-the-art approaches without using prior training or requiring particular features.
KW - Music/Voice Separation
KW - Robust Principal Component Analysis
KW - Time-Frequency Masking
UR - http://www.scopus.com/inward/record.url?scp=84867585384&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84867585384&partnerID=8YFLogxK
U2 - 10.1109/ICASSP.2012.6287816
DO - 10.1109/ICASSP.2012.6287816
M3 - Conference contribution
AN - SCOPUS:84867585384
SN - 9781467300469
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 57
EP - 60
BT - 2012 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2012 - Proceedings
T2 - 2012 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2012
Y2 - 25 March 2012 through 30 March 2012
ER -