Detail publikace

Feature comparison under different noise conditions for gunshot detection task

Originální název

Feature comparison under different noise conditions for gunshot detection task

Anglický název

Feature comparison under different noise conditions for gunshot detection task

Jazyk

en

Originální abstrakt

Presented work investigates performance of three feature sets (LPC, LPCC and MFCC) in distinguishing gunshots from non-gunshot, mostly urban sounds under white noise conditions ranging from 30 dB to 0 dB with 10 dB step, including clean signal. Results show, that LPC coefficients are best at 30 dB with comparable results achieved by LPCC. MFCC are significantly better than others at 20 dB and 10 dB. Performance at 0 dB was balanced between LPC and MFCC – LPC had more true detections and MFCC achieved better score for false alarms.

Anglický abstrakt

Presented work investigates performance of three feature sets (LPC, LPCC and MFCC) in distinguishing gunshots from non-gunshot, mostly urban sounds under white noise conditions ranging from 30 dB to 0 dB with 10 dB step, including clean signal. Results show, that LPC coefficients are best at 30 dB with comparable results achieved by LPCC. MFCC are significantly better than others at 20 dB and 10 dB. Performance at 0 dB was balanced between LPC and MFCC – LPC had more true detections and MFCC achieved better score for false alarms.

BibTex


@inproceedings{BUT138779,
  author="Martin {Hrabina} and Milan {Sigmund}",
  title="Feature comparison under different noise conditions for gunshot detection task",
  annote="Presented work investigates performance of three feature sets (LPC, LPCC and MFCC) in distinguishing gunshots from non-gunshot, mostly urban sounds under white noise conditions ranging from 30 dB to 0 dB with 10 dB step, including clean signal. Results show, that LPC coefficients are best at 30 dB with comparable results achieved by LPCC. MFCC are significantly better than others at 20 dB and 10 dB. Performance at 0 dB was balanced between LPC and MFCC – LPC had more true detections and MFCC achieved better score for false alarms.",
  booktitle="Proceedings of IEEE Student Branch Conference Mikulov 2017",
  chapter="138779",
  edition="1",
  howpublished="online",
  year="2017",
  month="august",
  pages="29--33",
  type="conference paper"
}