Feature comparison under different noise conditions for gunshot detection task

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26220%2F17%3APU124446" target="_blank" >RIV/00216305:26220/17:PU124446 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
Feature comparison under different noise conditions for gunshot detection task
Original language description
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.
Czech name
—
Czech description
—

Project
<a href="/en/project/LO1401" target="_blank" >LO1401: Interdisciplinary Research of Wireless Technologies</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach

Publication year
2017
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
Proceedings of IEEE Student Branch Conference Mikulov 2017
ISBN
978-80-214-5526-9
ISSN
—
e-ISSN
—
Number of pages
4
Pages from-to
29-33
Publisher name
Neuveden
Place of publication
Neuveden
Event location
Mikulov, Czech republic
Event date
Aug 28, 2017
Type of event by nationality
EUR - Evropská akce
UT code for WoS article
—

Similar results(10)