Advanced Audio Signal Processing Methods for Automatic Classification of “Fire” and “Fireless” Sounds
Robert-Nicolae Boştinaru, Nicu Bizon, Sebastian–Alexandru Drăguşin, Gabriel–Vasile Iana, Denisa Toma · 2025
The automatic classification of “fire” and “fireless” sounds plays a crucial role in the development of intelligent fire warning and detection systems. This paper explores advanced methods of audio signal processing, with a focus on extracting relevant acoustic characteristics (Mel-Frequency Cepstral Coefficients (MFCC), Spectral Centroid, Zero Crossing Rate (ZCR)), used to train automatic classification models. Challenges such as ambient noise, spectral variability and feature redundancy are analyzed. The study demonstrates the potential of acoustic processing technologies in improving early fire detection systems in real-world environments.