Separation of Harmonic Musical Instrument Notes Using Spectro-Temporal Modeling of Harmonic Magnitudes and Spectrogram Inversion with Phase Optimization

Gunawan D, Sen D. Separation of Harmonic Musical Instrument Notes Using Spectro-Temporal Modeling of Harmonic Magnitudes and Spectrogram Inversion with Phase Optimization. J Audio Eng Soc. 2012;60(12):1004-1014. Available from: https://aes.org/publications/elibrary-page/?id=16641

@article{Gunawan2012_16641,
  author = {Gunawan, David and Sen, Deep},
  title = {{Separation of Harmonic Musical Instrument Notes Using Spectro-Temporal Modeling of Harmonic Magnitudes and Spectrogram Inversion with Phase Optimization}},
  journal = {Journal of the Audio Engineering Society},
  volume = {60},
  number = {12},
  pages = {1004--1014},
  year = {2012},
  month = dec,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=16641}
}

TY  - JOUR
TI  - Separation of Harmonic Musical Instrument Notes Using Spectro-Temporal Modeling of Harmonic Magnitudes and Spectrogram Inversion with Phase Optimization
AU  - Gunawan, David
AU  - Sen, Deep
T2  - Journal of the Audio Engineering Society
J2  - J. Audio Eng. Soc.
VL  - 60
IS  - 12
SP  - 1004
EP  - 1014
PY  - 2012
DA  - 2012/12/06
UR  - https://aes.org/publications/elibrary-page/?id=16641
PB  - Audio Engineering Society
LA  - en
AB  - Separating the individual sources in a single channel is particularly difficult because of overlapping harmonics. Western music is often arranged so that sounds are not only occurring simultaneously, but are also harmonically related. While traditional approaches use either spectral or temporal models, the proposed model exploits the combination of the spectral and temporal correlations of harmonic magnitudes to estimate the regions of overlap. A diverse selection of harmonic musical instruments was analyzed, and a generalized-instrument magnitude track prediction model was derived to generate track estimates. This approach, which exploits dependencies among tracks, was shown to be consistently more accurate than existing methods.
ER  -