Demixing Commercial Music Productions via Human-Assisted Time-Frequency Masking

Bonada J, Loscos A, Vinyes M. Demixing Commercial Music Productions via Human-Assisted Time-Frequency Masking. In: AES Convention 120. Audio Engineering Society; 2006. Paper 6719. Available from: https://aes.org/publications/elibrary-page/?id=13523

@inproceedings{Bonada2006_13523,
  author = {Bonada, Jordi and Loscos, Alex and Vinyes, Marc},
  title = {{Demixing Commercial Music Productions via Human-Assisted Time-Frequency Masking}},
  booktitle = {AES Convention 120},
  note = {Paper 6719},
  year = {2006},
  month = may,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=13523}
}

TY  - CPAPER
TI  - Demixing Commercial Music Productions via Human-Assisted Time-Frequency Masking
AU  - Bonada, Jordi
AU  - Loscos, Alex
AU  - Vinyes, Marc
T2  - AES Convention 120
M1  - Paper 6719
PY  - 2006
DA  - 2006/05/06
UR  - https://aes.org/publications/elibrary-page/?id=13523
PB  - Audio Engineering Society
LA  - en
AB  - Audio Blind Separation in real commercial music recordings is still an open problem. In the last few years some techniques have provided interesting results. This article presents a human-assisted clusterization of the DFT coefficients for the Time-Frequency Masking demixing technique. The DFT coefficients are grouped by adjacent panning and phase difference and an interactive graphical interface allows the user to select in real-time panning and phase difference ranges for each song. Results prove an implementation of such technique can be used to demix tracks from nowadays commercial songs. Sample sounds can be found here: http://www.iua.upf.es/~mvinyes/abs/demos
ER  -