TY - GEN
T1 - An adaptive time-frequency resolution framework for single channel source separation based on non-negative tensor factorization
AU - Kirbiz, S.
AU - Gunsel, B.
PY - 2013/10/18
Y1 - 2013/10/18
N2 - In this paper, we propose an adaptive time-frequency resolution based single channel sound source separation method using Non-negative Tensor Factorization (NTF). The model aims to alleviate drawbacks of working by fixed length Short Time Fourier Transform (STFT) by minimizing the smearing of signal energy in both time and frequency. A joint optimization scheme has been applied based on KL-divergence where each layer of the tensor represents the mixture at a different resolution. In order to enclose sparseness into factorization, the resynthesis is made through an adaptive weighted fusion procedure which combines the separated sources in a manner that maximizes the energy concentration. Test results reported over a large sound database indicate the introduced NTF based fusion method improves the sound quality both in terms of conventional and perceptual distortion measures.
AB - In this paper, we propose an adaptive time-frequency resolution based single channel sound source separation method using Non-negative Tensor Factorization (NTF). The model aims to alleviate drawbacks of working by fixed length Short Time Fourier Transform (STFT) by minimizing the smearing of signal energy in both time and frequency. A joint optimization scheme has been applied based on KL-divergence where each layer of the tensor represents the mixture at a different resolution. In order to enclose sparseness into factorization, the resynthesis is made through an adaptive weighted fusion procedure which combines the separated sources in a manner that maximizes the energy concentration. Test results reported over a large sound database indicate the introduced NTF based fusion method improves the sound quality both in terms of conventional and perceptual distortion measures.
KW - adaptive time-frequency resolution
KW - Non-negative Tensor Factorization
KW - sound source separation
UR - http://www.scopus.com/inward/record.url?scp=84890485034&partnerID=8YFLogxK
U2 - 10.1109/ICASSP.2013.6637780
DO - 10.1109/ICASSP.2013.6637780
M3 - Conference contribution
AN - SCOPUS:84890485034
SN - 9781479903566
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 905
EP - 909
BT - 2013 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013 - Proceedings
T2 - 2013 38th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013
Y2 - 26 May 2013 through 31 May 2013
ER -