Fsd50k: an open dataset of human-labeled sound events

E Fonseca, X Favory, J Pons, F Font… - IEEE/ACM Transactions …, 2021‏ - ieeexplore.ieee.org
Most existing datasets for sound event recognition (SER) are relatively small and/or domain-
specific, with the exception of AudioSet, based on over 2 M tracks from YouTube videos and …

Gunshots detection, identification, and classification: Applications to forensic science

Y Teng, K Zhang, X Lv, Q Miao, T Zang, A Yu, A Hui… - Science & Justice, 2024‏ - Elsevier
The proliferation of audio sensors in surveillance, smartphones, and numerous devices has
made gunshots-based event detection and forensic analysis critical for prompt police action …

Dominant noise-aided EMD (DEMD): Extending empirical mode decomposition for noise reduction by incorporating dominant noise and deep classification

Z Shamaee, M Mivehchy - Biomedical Signal Processing and Control, 2023‏ - Elsevier
Biomedical signals are frequently contaminated by colored noise; consequently, noise
recognition and reduction are critical to biomedical systems. Conventional techniques have …

Sound of guns: digital forensics of gun audio samples meets artificial intelligence

S Raponi, G Oligeri, IM Ali - Multimedia tools and applications, 2022‏ - Springer
Classifying a weapon based on its muzzle blast is a challenging task that has significant
applications in various security and military fields. Most of the existing works rely on ad-hoc …

[HTML][HTML] A fast identification method of gunshot types based on knowledge distillation

J Li, J Guo, X Sun, C Li, L Meng - Applied Sciences, 2022‏ - mdpi.com
To reduce the large size of a gunshot recognition network model and to improve the
insufficient real-time detection in urban combat, this paper proposes a fast gunshot type …

An automated gunshot audio classification method based on finger pattern feature generator and iterative relieff feature selector

T Tuncer, S Dogan, E Akbal… - Adıyaman Üniversitesi …, 2021‏ - dergipark.org.tr
Audio forensics applications and methods are very crucial to clarify crimes. To accelerate
audio analysis process and classify audios with high accuracy, machine learning (ML) …

A new fractal H-tree pattern based gun model identification method using gunshot audios

S Dogan - Applied Acoustics, 2021‏ - Elsevier
Background Gun model identification (GMI) is a complex issue for digital forensics
examiners/professions. Because the GMI process is a highly costed process, and it is …

[HTML][HTML] A gunshot recognition method based on multi-scale spectrum shift module

J Li, J Guo, M Ma, Y Zeng, C Li, J Xu - Electronics, 2022‏ - mdpi.com
In view of the issues such as the larger network model and lower recognition accuracy of the
current gunshot recognition networks, a neural network based on a multi-scale spectrum …

Feature extraction of surround sound recordings for acoustic scene classification

SK Zieliński - Artificial Intelligence and Soft Computing: 17th …, 2018‏ - Springer
This paper extends the traditional methodology of acoustic scene classification based on
machine listening towards a new class of multichannel audio signals. It identifies a set of …

Effect of sampling rate reduction and signal filtering for gunfire sound classification with spectral vector using ANN

S Tangkawanit, S Kanprachar - ECTI Transactions on Electrical …, 2020‏ - ph02.tci-thaijo.org
To identify the type of the shooting gun, there are many important parameters to be
considered. One key feature is the gunfire sound. It has been shown [1, 2] that applying the …