Detail publikace

Gunshot Recognition using Low Level Features in the Time Domain

Originální název

Gunshot Recognition using Low Level Features in the Time Domain

Anglický název

Gunshot Recognition using Low Level Features in the Time Domain

Jazyk

en

Originální abstrakt

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.

Anglický abstrakt

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.

Plný text v Digitální knihovně

BibTex


@inproceedings{BUT147072,
  author="Martin {Hrabina} and Milan {Sigmund}",
  title="Gunshot Recognition using Low Level Features in the Time Domain",
  annote="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.",
  address="IEEE",
  booktitle="Proceedings of 28th International Conference Radioelektronika 2018",
  chapter="147072",
  doi="10.1109/RADIOELEK.2018.8376372",
  howpublished="online",
  institution="IEEE",
  year="2018",
  month="april",
  pages="1--5",
  publisher="IEEE",
  type="conference paper"
}