D. Barry, E. Coyle, D. Fitzgerald, and R. Lawlor, “Single Channel Source Separation Using Short-Time Independent Component Analysis,” in Proc. AES Convention 119, Oct. 2005, pp. 6603:1-6. [Online]. Available: https://aes.org/publications/elibrary-page/?id=13364
Barry D, Coyle E, Fitzgerald D, Lawlor R. Single Channel Source Separation Using Short-Time Independent Component Analysis. In: AES Convention 119. Audio Engineering Society; 2005.pp. 6603:1-6. Available from: https://aes.org/publications/elibrary-page/?id=13364
@inproceedings{Barry2005_13364,
author = {Barry, Dan and Coyle, Eugene and Fitzgerald, Derry and Lawlor, Robert},
title = {{Single Channel Source Separation Using Short-Time Independent Component Analysis}},
booktitle = {AES Convention 119},
pages = {6603:1-6},
url = {https://aes.org/publications/elibrary-page/?id=13364},
year = {2005},
month = oct,
publisher = {Audio Engineering Society},
address = {New York}
}
TY - CPAPER
TI - Single Channel Source Separation Using Short-Time Independent Component Analysis
AU - Barry, Dan
AU - Coyle, Eugene
AU - Fitzgerald, Derry
AU - Lawlor, Robert
T2 - AES Convention 119
SP - 1
EP - 6
M1 - Paper 6603
PY - 2005
DA - 2005/10/06
UR - https://aes.org/publications/elibrary-page/?id=13364
PB - Audio Engineering Society
CY - New York
LA - en
AB - In this paper we develop a method for the sound source separation of single channel mixtures using Independent Component Analysis within a time-frequency representation of the audio signal. We apply standard Independent Component Analysis techniques to contiguous magnitude frames of the short-time Fourier transform of the mixture. Provided that the amplitude envelopes of each source are sufficiently different, it can be seen that it is possible to recover the independent short-time power spectra of each source. A simple scoring scheme based on auditory scene analysis cues is then used to overcome the source ordering problem ultimately allowing each of the independent spectra to be assigned to the correct output source. A final stage of adaptive filtering is then applied which forces each of the spectra to become more independent. Each of the sources is then resynthesised using the standard inverse short-time Fourier transform and overlap add scheme.
ER -