Firearm classification from acoustic signals using combined mel spectrogram, MFCC, LFCC, and CRNN networks
Lamine Elkarous, Mohamed Hechmi Jeridi, Montassar Dhouibi · 2025
Read Firearm classification from acoustic signals using combined mel spectrogram, MFCC, LFCC, and CRNN networks by Lamine Elkarous, Mohamed Hechmi Jeridi, Montassar Dhouibi (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-12717235.txt.
Description
Lamine Elkarous, Mohamed Hechmi Jeridi, and Montassar Dhouibi built a system to name firearm types from gunshot sounds in two thousand twenty-five. Telling guns apart by sound is hard because echoes, noise, and setting change each shot's fingerprint. A working system also needs to run in real time.
Their system records shots with small microphones, cleans the signal, and pulls out a mixed feature set from sound spectra. A deep network that blends convolutional and recurrent parts then classifies the firearm type. Tests showed the system could work in real time with a good balance of accuracy and speed. Extreme conditions still hurt its results, the authors note.
Catalog record
| CREATOR | Lamine Elkarous, Mohamed Hechmi Jeridi, Montassar Dhouibi |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 86 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |