A Comparison of Computational Precedence Models for Source Separation in Reverberant Environments

Hummersone C, Mason R, Brookes T. A Comparison of Computational Precedence Models for Source Separation in Reverberant Environments. J Audio Eng Soc. 2013;61(7/8):508-520. Available from: https://aes.org/publications/elibrary-page/?id=16867

@article{Hummersone2013_16867,
  author = {Hummersone, Christopher and Mason, Russell and Brookes, Tim},
  title = {{A Comparison of Computational Precedence Models for Source Separation in Reverberant Environments}},
  journal = {Journal of the Audio Engineering Society},
  volume = {61},
  number = {7/8},
  pages = {508--520},
  year = {2013},
  month = jul,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=16867}
}

TY  - JOUR
TI  - A Comparison of Computational Precedence Models for Source Separation in Reverberant Environments
AU  - Hummersone, Christopher
AU  - Mason, Russell
AU  - Brookes, Tim
T2  - Journal of the Audio Engineering Society
J2  - J. Audio Eng. Soc.
VL  - 61
IS  - 7/8
SP  - 508
EP  - 520
PY  - 2013
DA  - 2013/07/06
UR  - https://aes.org/publications/elibrary-page/?id=16867
PB  - Audio Engineering Society
LA  - en
AB  - Reverberation is a problem for source separation algorithms. Because the precedence effect allows human listeners to suppress the perception of reflections arising from room boundaries, numerous computational models have incorporated the precedence effect. However, relatively little work has been done on using the precedence effect in source separation algorithms. This paper compares several precedence models and their influence on the performance of a baseline separation algorithm. The models were tested in a variety of reverberant rooms and with a range of mixing parameters. Although there was a large difference in performance among the models, the one that was based on interaural coherence and onset-based inhibition produced the greatest performance improvement. There is a trade-off between selecting reliable cues that correspond closely to free-field conditions and maximizing the proportion of the input signals that contributes to localization. For optimal source separation performance, it is necessary to adapt the dynamic component of the precedence model to the acoustic conditions of the room.
ER  -