Publication detail

Gunshot Recognition using Low Level Features in the Time Domain

HRABINA, M. SIGMUND, M.

Original Title

Gunshot Recognition using Low Level Features in the Time Domain

Type

conference paper

Language

English

Original Abstract

This paper explores the possibility of using scarcely used time-domain features for the task of gunshot recognition. A set of 11 features derived from temporal characteristics (waveform) of signals is calculated from a mixed dataset of gunshots and non-gunshots. The features leverage the impulsive nature of gunshots and their dissimilarity to other, especially more stationary signals. The paper includes a description of feature extraction, distribution of features and their recognition performance on a selected audio dataset. A subset achieves promising results in comparison with more frequently used spectral-domain features. This makes them a valuable addition to other frequently used features, especially for tasks of impulsive sound recognition.

Keywords

gunshot detection, feature extraction, time-domain features, audio processing

Authors

HRABINA, M.; SIGMUND, M.

Released

19. 4. 2018

Publisher

IEEE

ISBN

978-1-5386-2485-2

Book

Proceedings of 28th International Conference Radioelektronika 2018

Pages from

1

Pages to

5

Pages count

5

URL

Full text in the Digital Library

BibTex

@inproceedings{BUT147072,
  author="Martin {Hrabina} and Milan {Sigmund}",
  title="Gunshot Recognition using Low Level Features in the Time Domain",
  booktitle="Proceedings of 28th International Conference Radioelektronika 2018",
  year="2018",
  pages="1--5",
  publisher="IEEE",
  doi="10.1109/RADIOELEK.2018.8376372",
  isbn="978-1-5386-2485-2",
  url="https://ieeexplore.ieee.org/document/8376372/"
}