Onset-Based Sound Segmentation

Abstract

A technique for segmenting sounds using processing based on mam(cid:173) malian early auditory processing is presented. The technique is based on features in sound which neuron spike recording suggests are detected in the cochlear nucleus. The sound signal is band(cid:173) passed and each signal processed to enhance onsets and offsets. The onset and offset signals are compressed, then clustered both in time and across frequency channels using a network of integrate(cid:173) and-fire neurons. Onsets and offsets are signalled by spikes, and the timing of these spikes used to segment the sound.

Cite

Text

Smith. "Onset-Based Sound Segmentation." Neural Information Processing Systems, 1995.

Markdown

[Smith. "Onset-Based Sound Segmentation." Neural Information Processing Systems, 1995.](https://mlanthology.org/neurips/1995/smith1995neurips-onsetbased/)

BibTeX

@inproceedings{smith1995neurips-onsetbased,
  title     = {{Onset-Based Sound Segmentation}},
  author    = {Smith, Leslie S.},
  booktitle = {Neural Information Processing Systems},
  year      = {1995},
  pages     = {729-735},
  url       = {https://mlanthology.org/neurips/1995/smith1995neurips-onsetbased/}
}