Acoustic Pre-training with Contrastive Learning for Gunshot Recognition
Authors: 
Xianjie Shen, Saimin Ma, Linlin Yang, Yubo Jiang, Zhifeng Xiao, Shu XuAuthors Info & Claims
Pages 714 - 719
Abstract
Gun control has become a serious social and political issue in some countries. Automatic, accurate, and fast gunshot recognition technology can assist police in the identification of gun caliber, thus help better track the suspect, speeding up the process of criminal investigation. Recent development in deep learning has brought new opportunities in the area of speech/acoustic recognition. However, lack of sufficient training examples remains a challenge for the training of a robust model. In this paper, we propose an acoustic pre-training method with contrastive learning to capture gunshot-like voice in a rich collection of urban sounds. Specifically, we develop an encoder-decoder model that utilizes more typical samples from external datasets to mine semantic acoustic features in a self-supervised manner. The pre-trained network is then fine-tuned in the downstream task for gunshot recognition. Extensive experiments demonstrate the superiority of our methods compared to existing machine learning methods.
References
[1]
Tanav Aggarwal, Nonita Sharma, and Naveen Aggarwal. 2022. Gunshot Detection and Classification Using a Convolution-GRU Based Approach. In Proceedings of Emerging Trends and Technologies on Intelligent Systems: ETTIS 2022. Springer, Singapore, 95–107.
[2]
Talal Ahmed, Momin Uppal, and Abubakr Muhammad. 2013. Improving efficiency and reliability of gunshot detection systems. In 2013 IEEE International Conference on Acoustics, Speech and Signal Processing. IEEE, IEEE, Vancouver, BC, Canada, 513–517.
[3]
Shahin Amiriparian, N Cummins, S Julka, and Björn Schuller. 2018. Deep convolutional recurrent neural network for rare acoustic event detection. In Proc. DAGA. IEEE, Vancouver, BC, Canada, 1522–1525.
[4]
Behnaz Bahmei, Elina Birmingham, and Siamak Arzanpour. 2022. CNN-RNN and data augmentation using deep convolutional generative adversarial network for environmental sound classification. IEEE Signal Processing Letters 29 (2022), 682–686.
[5]
Jakub Bajzik, Jiri Prinosil, and Dusan Koniar. 2020. Gunshot detection using convolutional neural networks. In 2020 24th International Conference Electronics. IEEE, IEEE, Palanga, Lithuania, 1–5.
[6]
Christian Busse, Thomas Krause, Jörn Ostermann, and Jörg Bitzer. 2019. Improved gunshot classification by using artificial data. In Audio Engineering Society Conference: 2019 AES International Conference on Audio Forensics. Audio Engineering Society, ACM, Porto, 5526.
[7]
Xinlei Chen, Haoqi Fan, Ross Girshick, and Kaiming He. 2020. Improved baselines with momentum contrastive learning. arXiv preprint arXiv:2003.04297 29 (2020), 1015–1018.
[8]
Andrew Digby, Michael Towsey, Ben D Bell, and Paul D Teal. 2013. A practical comparison of manual and autonomous methods for acoustic monitoring. Methods in Ecology and Evolution 4, 7 (2013), 675–683.
[9]
Mona Fawaz, Mona Harb, and Ahmad Gharbieh. 2012. Living Beirut’s security zones: An investigation of the modalities and practice of urban security. City & Society 24, 2 (2012), 173–195.
[10]
Tianyu Gao, Xingcheng Yao, and Danqi Chen. 2021. Simcse: Simple contrastive learning of sentence embeddings. arXiv preprint arXiv:2104.08821 33 (2021), 21271–21284.
[11]
Kaiming He, Haoqi Fan, Yuxin Wu, Saining Xie, and Ross Girshick. 2020. Momentum contrast for unsupervised visual representation learning. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. IEEE, xian, 9729–9738.
[12]
Martin Hrabina and Milan Sigmund. 2018. Gunshot recognition using low level features in the time domain. In 2018 28th International Conference Radioelektronika (RADIOELEKTRONIKA). IEEE, IEEE, xian, 1–5.
[13]
Eva Kiktova, Martin Lojka, Matus Pleva, Jozef Juhar, and Anton Cizmar. 2015. Gun type recognition from gunshot audio recordings. In 3rd international workshop on biometrics and forensics (IWBF 2015). IEEE, IEEE, London, 1–6.
[14]
Jian Li, Jinming Guo, Xiushan Sun, Chuankun Li, and Lingpeng Meng. 2022. A fast identification method of gunshot types based on knowledge distillation. Applied Sciences 12, 11 (2022), 5526.
[15]
Alex Morehead, Lauren Ogden, Gabe Magee, Ryan Hosler, Bruce White, and George Mohler. 2019. Low cost gunshot detection using deep learning on the raspberry pi. In 2019 IEEE International Conference on Big Data (Big Data). IEEE, IEEE, xian, 3038–3044.
[16]
Karol J Piczak. 2015. ESC: Dataset for environmental sound classification. In Proceedings of the 23rd ACM international conference on Multimedia. ACM, xian, 1015–1018.
[17]
Sami Ur Rahman, Adnan Khan, Sohail Abbas, Fakhre Alam, and Nasir Rashid. 2021. Hybrid system for automatic detection of gunshots in indoor environment. Multimedia Tools and Applications 80 (2021), 4143–4153.
[18]
Simone Raponi, Gabriele Oligeri, and Isra Mohamed Ali. 2022. Sound of guns: digital forensics of gun audio samples meets artificial intelligence. Multimedia tools and applications 81, 21 (2022), 30387–30412.
[19]
Justin Salamon and Juan Pablo Bello. 2017. Deep convolutional neural networks and data augmentation for environmental sound classification. IEEE Signal processing letters 24, 3 (2017), 279–283.
[20]
Rajesh Baliram Singh and Hanqi Zhuang. 2022. Measurements, analysis, classification, and detection of gunshot and gunshot-like sounds. Sensors 22, 23 (2022), 9170.
Index Terms
- Acoustic Pre-training with Contrastive Learning for Gunshot Recognition
Recommendations
MimCo: Masked Image Modeling Pre-training with Contrastive Teacher
MM '22: Proceedings of the 30th ACM International Conference on MultimediaRecent masked image modeling (MIM) has received much attention in self-supervised learning (SSL), which requires the target model to recover the masked part of the input image. Although MIM-based pre-training methods achieve new state-of-the-art ...
Poster: Boosting Adversarial Robustness by Adversarial Pre-training
CCS '23: Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications SecurityVision Transformer (ViT) shows superior performance on various tasks, but, similar to other deep learning techniques, it is vulnerable to adversarial attacks. Due to the differences between ViT and traditional CNNs, previous works designed new ...
A fast and efficient pre-training method based on layer-by-layer maximum discrimination for deep neural networks
In this paper, through extension of the present methods and based on error minimization, two fast and efficient layer-by-layer pre-training methods are proposed for initializing deep neural network (DNN) weights. Due to confrontation with a large number ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
May 2023
1025 pages
ISBN:9798400700705
DOI:10.1145/3603781
Copyright © 2023 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 27 July 2023
Check for updates
Author Tags
Qualifiers
- Research-article
- Research
- Refereed limited
Conference
CNIOT'23
CNIOT'23: 2023 4th International Conference on Computing, Networks and Internet of Things
May 26 - 28, 2023
Xiamen, China
Acceptance Rates
Overall Acceptance Rate 39 of 82 submissions, 48%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 28Total Downloads
- Downloads (Last 12 months)14
- Downloads (Last 6 weeks)2
Reflects downloads up to 17 Nov 2024
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign inFull Access
View options
View or Download as a PDF file.
PDFeReader
View online with eReader.
eReaderHTML Format
View this article in HTML Format.
HTML Format