Přístupnostní navigace
E-přihláška
Vyhledávání Vyhledat Zavřít
Detail publikace
HRABINA, M.
Originální název
Optimization of Mel-Frequency Cepstral Coefficients for Automatic Gunshot Detection
Typ
článek ve sborníku ve WoS nebo Scopus
Jazyk
angličtina
Originální abstrakt
Mel-frequency cepstral coefficients (MFCCs) are features widely used in tasks such as sound event detection (SED), speech recognition or other audio processing problems. This paper explores various ways of modification MFCCs in order to achieve optimal detection results for gunshot detection task. The paper focuses especially on frequency scale and bandwidth, number of filter banks and filter bank shape. The final results achieve recognition performance of 98.7 true negative rate (TNR) and 84.8 true positive rate (TPR).
Klíčová slova
gunshot detection, mel-frequency cepstral coefficients, optimization
Autoři
Vydáno
10. 9. 2019
ISBN
978-80-214-5781-2
Kniha
Proceedings of IEEE Student Branch Conference Mikulov 2019
Strany od
46
Strany do
48
Strany počet
3
BibTex
@inproceedings{BUT159769, author="Martin {Hrabina}", title="Optimization of Mel-Frequency Cepstral Coefficients for Automatic Gunshot Detection", booktitle="Proceedings of IEEE Student Branch Conference Mikulov 2019", year="2019", pages="46--48", isbn="978-80-214-5781-2" }