Systematic benchmark of feature extraction techniques and parameters for gunshot audio classification shows up to 20% top-1 accuracy gain from technique choice and 4.7% from parameter tuning on a 23k-recording dataset.
On desensitizing the Mel-cepstrum to spurious spectral components for robust speech recognition,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Exploring Feature Extraction Technique Parameters for Acoustic Gunshot Classification
Systematic benchmark of feature extraction techniques and parameters for gunshot audio classification shows up to 20% top-1 accuracy gain from technique choice and 4.7% from parameter tuning on a 23k-recording dataset.