Detail publikace

Comparison of Feature Performance in Gunshot Detection Depending on Noise Degradation

Originální název

Comparison of Feature Performance in Gunshot Detection Depending on Noise Degradation

Anglický název

Comparison of Feature Performance in Gunshot Detection Depending on Noise Degradation

Jazyk

en

Originální abstrakt

This paper compares three different features and various feature orders for the purpose of determining the best feature for gunshot detection under adverse noise condition. Compared features cover LPC, LPCC and MFCC with orders from 8 to 30. All features were extracted from sounds with the sound-to-noise ratios 30, 20, 10, and 0 dB. The background noise was simulated by white noise. Experimental results indicate that LPC coefficients are the most efficient features, especially for low noise. On the other hand, MFCC performed well in noisy environments at 10 dB and 20 dB.

Anglický abstrakt

This paper compares three different features and various feature orders for the purpose of determining the best feature for gunshot detection under adverse noise condition. Compared features cover LPC, LPCC and MFCC with orders from 8 to 30. All features were extracted from sounds with the sound-to-noise ratios 30, 20, 10, and 0 dB. The background noise was simulated by white noise. Experimental results indicate that LPC coefficients are the most efficient features, especially for low noise. On the other hand, MFCC performed well in noisy environments at 10 dB and 20 dB.

BibTex


@inproceedings{BUT135464,
  author="Martin {Hrabina} and Milan {Sigmund}",
  title="Comparison of Feature Performance in Gunshot Detection Depending on Noise Degradation",
  annote="This paper compares three different features and
various feature orders for the purpose of determining the best
feature for gunshot detection under adverse noise condition.
Compared features cover LPC, LPCC and MFCC with orders
from 8 to 30. All features were extracted from sounds with the
sound-to-noise ratios 30, 20, 10, and 0 dB. The background noise
was simulated by white noise. Experimental results indicate that
LPC coefficients are the most efficient features, especially for low
noise. On the other hand, MFCC performed well in noisy
environments at 10 dB and 20 dB.",
  booktitle="Proceedings of 27th International Conference Radioelektronika 2017",
  chapter="135464",
  doi="10.1109/RADIOELEK.2017.7937601",
  howpublished="electronic, physical medium",
  year="2017",
  month="april",
  pages="223--226",
  type="conference paper"
}