Fusing Grouping Cues for Partials Using Artificial Neural Networks

Every M, Litwic L. Fusing Grouping Cues for Partials Using Artificial Neural Networks. In: AES Conference: 30th International Conference: Intelligent Audio Environments. Audio Engineering Society; 2007. Paper 24. Available from: https://aes.org/publications/elibrary-page/?id=13923

@inproceedings{Every2007_13923,
  author = {Every, Mark and Litwic, Lukasz},
  title = {{Fusing Grouping Cues for Partials Using Artificial Neural Networks}},
  booktitle = {AES Conference: 30th International Conference: Intelligent Audio Environments},
  note = {Paper 24},
  year = {2007},
  month = mar,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=13923}
}

TY  - CPAPER
TI  - Fusing Grouping Cues for Partials Using Artificial Neural Networks
AU  - Every, Mark
AU  - Litwic, Lukasz
T2  - AES Conference: 30th International Conference: Intelligent Audio Environments
M1  - Paper 24
PY  - 2007
DA  - 2007/03/06
UR  - https://aes.org/publications/elibrary-page/?id=13923
PB  - Audio Engineering Society
LA  - en
AB  - The primary stages of auditory stream separation are modelled here as a bottom-up organisation of primitive spectro-temporal regions into composites, which provide a succinct description of the sound environment in terms of a limited number of salient sound events. Many years of research on auditory streaming have determined a number of qualitative comparisons between physical attributes of sounds, or cues, that are well-correlated with the extent to which stream segregation or fusion of simple test stimuli occurs in listening tests. However, the relative importance of these cues is difficult to determine, especially in natural sound environments. This work represents some exploratory stages in using an artificial neural network to learn how to integrate multiple cues in nonlinear manner, for sound object formation. As a precursor to a more complex auditory front-end, a sinusoidal tracking algorithm was used to obtain the initial set of "spectro-temporal regions" or partial trajectories.
ER  -