245 Hits in 5.3 sec

Compression of Acoustic Event Detection Models with Quantized Distillation

Bowen Shi, Ming Sun, Chieh-Chi Kao, Viktor Rozgic, Spyros Matsoukas, Chao Wang
2019 Interspeech 2019  
Acoustic Event Detection (AED), aiming at detecting categories of events based on audio signals, has found application in many intelligent systems.  ...  In this paper, we present a simple yet effective compression approach which jointly leverages knowledge distillation and quantization to compress larger network (teacher model) into compact network (student  ...  Conclusion We study the model compression problem in the context of acoustic event detection. Our compression scheme jointly applies knowledge distillation and quantization to the target model.  ... 
doi:10.21437/interspeech.2019-1747 dblp:conf/interspeech/ShiSKRMW19 fatcat:cppoyd7orfgenpcyvpogtbf4dq

Compact recurrent neural networks for acoustic event detection on low-energy low-complexity platforms

Gianmarco Cerutti, Rahul Prasad, Alessio Brutti, Elisabetta Farella
2020 IEEE Journal on Selected Topics in Signal Processing  
Outdoor acoustic events detection is an exciting research field but challenged by the need for complex algorithms and deep learning techniques, typically requiring many computational, memory, and energy  ...  This paper addresses the application of sound event detection at the edge, by optimizing deep learning techniques on resource-constrained embedded platforms for the IoT.  ...  Nevertheless, advances in terms of accuracy and robustness of current acoustic event detection algorithms are achieved by using large neural networks, which are increasingly hungry in terms of computational  ... 
doi:10.1109/jstsp.2020.2969775 fatcat:pjsjujou6zcj7i2jggmgsgcwla

Domain Generalization on Efficient Acoustic Scene Classification using Residual Normalization [article]

Byeonggeun Kim, Seunghan Yang, Jangho Kim, Simyung Chang
2021 arXiv   pre-print
Through three model compression schemes: pruning, quantization, and knowledge distillation, we can reduce model complexity further while mitigating the performance degradation.  ...  The proposed system achieves an average test accuracy of 76.3% in TAU Urban Acoustic Scenes 2020 Mobile, development dataset with 315k parameters, and average test accuracy of 75.3% after compression to  ...  Detection and Classification of Acoustic Scenes and Events (DCASE) [4] is an annual challenge, attracting attention to the field.  ... 
arXiv:2111.06531v1 fatcat:4utau2k3fnb6pn6lguy5ajii3q

A Lottery Ticket Hypothesis Framework for Low-Complexity Device-Robust Neural Acoustic Scene Classification [article]

Hao Yen, Chao-Han Huck Yang, Hu Hu, Sabato Marco Siniscalchi, Qing Wang, Yuyang Wang, Xianjun Xia, Yuanjun Zhao, Yuzhong Wu, Yannan Wang, Jun Du, Chin-Hui Lee
2022 arXiv   pre-print
Acoustic Lottery could compress an ASC model up to 1/10^4 and attain a superior performance (validation accuracy of 79.4 and Log loss of 0.64) compared to its not compressed seed model.  ...  We propose a novel neural model compression strategy combining data augmentation, knowledge transfer, pruning, and quantization for device-robust acoustic scene classification (ASC).  ...  The Detection and Classification of Acoustic Scenes and Events (DCASE) challenges [2, 3, 4, 5] provide a comprehensive evaluation platform and benchmark data to encourage and boost sound scene research  ... 
arXiv:2107.01461v4 fatcat:7ibt335h4bavbpg67jgapky3nm

Editorial: Special Issue on Compact Deep Neural Networks With Industrial Applications

Lixin Fan, Diana Marculescu, Werner Bailer, Yurong Chen
2020 IEEE Journal on Selected Topics in Signal Processing  
In "Compact Recurrent Neural Networks for Acoustic Event Detection on Low-Energy Low-Complexity Platforms", Cerutti et al. address the application of sound event detection at the edge, by optimizing deep  ...  The proposed scheme compresses the MobileNet and ShuffleNet models trained on ImageNet with the state-of-the-art compression ratios of 10.7 and 8.8, respectively.  ... 
doi:10.1109/jstsp.2020.3006323 fatcat:d75ni7ocajb4pemovq2l3ton4i

Knowledge Distillation: A Survey [article]

Jianping Gou, Baosheng Yu, Stephen John Maybank, Dacheng Tao
2021 arXiv   pre-print
As a representative type of model compression and acceleration, knowledge distillation effectively learns a small student model from a large teacher model.  ...  To this end, a variety of model compression and acceleration techniques have been developed.  ...  For efficient acoustic event detection, a quantized distillation method is proposed by using both knowledge distillation and quantization .  ... 
arXiv:2006.05525v6 fatcat:aedzaeln5zf3jgjsgsn5kvjrri

Scalable neural architectures for end-to-end environmental sound classification

Francesco Paissan, Alberto Ancilotto, Alessio Brutti, Elisabetta Farella
2022 Zenodo  
In particular, our architectures achieve state-of-the-art performance on UrbanSound8K in spectrogram classification (around 77%) with extreme compression factors (99.8%) with respect to current state-of-the-art  ...  In this paper, we propose novel neural architectures based on PhiNets for real-time acoustic event detection on microcontroller units.  ...  INTRODUCTION The task of Sound Event Detection (SED) consists in recognizing acoustic events in audio streams. This task is of interest both for industrial and smart cities applications.  ... 
doi:10.5281/zenodo.6351853 fatcat:bolkyk54pjbc3b3ikyhwte5wyq

Neural Network Distillation on IoT Platforms for Sound Event Detection

Gianmarco Cerutti, Rahul Prasad, Alessio Brutti, Elisabetta Farella
2019 Interspeech 2019  
In this paper, we consider the outdoor sound event detection task as a use case.  ...  However, in the emerging field of Internet of Things memory footprint and energy budget pose severe limits on the size and complexity of the neural models that can be implemented on embedded devices.  ...  These concepts apply to the scenarios of acoustic scene recognition and Sound Event Detection (SED) on which we focus in this work due to their applicability to smart city: traffic monitoring [5] , crowd  ... 
doi:10.21437/interspeech.2019-2394 dblp:conf/interspeech/CeruttiPBF19 fatcat:xafktaailbccto24dn6cg4uid4


F. de Vieilleville, A. Lagrange, R. Ruiloba, S. May
2020 The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences  
This method is presented through a ship detection example comparing accuracy and inference costs for several networks.  ...  To use them, we must reduce the size of DNN while accommodating efficiency in terms of both accuracy and inference cost.  ...  acknowledge the support from the CNES, French government Space Agency, and specially the DSO/SI/2A department, under the contract N° 190392/00 "Smart payloads" which allowed to perform a significant part of  ... 
doi:10.5194/isprs-archives-xliii-b2-2020-1553-2020 fatcat:fwlos5zfvzgtbmjw35xl37hcv4

2020 Index IEEE Journal of Selected Topics in Signal Processing Vol. 14

2020 IEEE Journal on Selected Topics in Signal Processing  
., +, JSTSP May 2020 884-893 Compact Recurrent Neural Networks for Acoustic Event Detection on Low-Energy Low-Complexity Platforms.  ...  Gamanayake, C., +, JSTSP May 2020 802-816 Compact Recurrent Neural Networks for Acoustic Event Detection on Low-Energy Low-Complexity Platforms.  ... 
doi:10.1109/jstsp.2020.3029672 fatcat:6twwzcqpwzg4ddcu2et75po77u

A Low-Compexity Deep Learning Framework For Acoustic Scene Classification [article]

Lam Pham, Hieu Tang, Anahid Jalali, Alexander Schindler, Ross King
2021 arXiv   pre-print
Our extensive experiments, which are conducted on DCASE 2021 (IEEE AASP Challenge on Detection and Classification of Acoustic Scenes and Events) Task 1A development dataset, achieve a low-complexity CNN  ...  To reduce the complexity of our proposed CNN network, we apply two model compression techniques: model restriction and decomposed convolution.  ...  In the future, we will further compress the model complexity by combining our proposed approaches with other techniques of distillation, pruning, and quantization.  ... 
arXiv:2106.06838v1 fatcat:hqzayvrbt5g2nhcmt4jap3yxgi

2020 Index IEEE Signal Processing Letters Vol. 27

2020 IEEE Signal Processing Letters  
., +, LSP 2020 71-75 Primary Quantization Matrix Estimation of Double Compressed JPEG Images via CNN.  ...  ., +, LSP 2020 1455-1459 Primary Quantization Matrix Estimation of Double Compressed JPEG Images via CNN.  ... 
doi:10.1109/lsp.2021.3055468 fatcat:wfdtkv6fmngihjdqultujzv4by

Monitoring Illegal Tree Cutting through Ultra-Low-Power Smart IoT Devices

Alessandro Andreadis, Giovanni Giambene, Riccardo Zambon
2021 Sensors  
Data obtained from the experimental results show that the proposed solution can detect and notify tree-cutting events for efficient and cost-effective forest monitoring through smart IoT, with an accuracy  ...  This paper proposes and evaluates a framework for automatically detecting illegal tree-cutting activity in forests through audio event classification.  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/s21227593 pmid:34833669 pmcid:PMC8624687 fatcat:33u2cfinw5darh5a2el4d7omk4

2021 Index IEEE Transactions on Multimedia Vol. 23

2021 IEEE transactions on multimedia  
The primary entry includes the coauthors' names, the title of the paper or other item, and its location, specified by the publication abbreviation, year, month, and inclusive pagination.  ...  Zhang, X., +, TMM 2021 1924-1937 Acoustic Room Modelling Using 360 Stereo Cameras. Kim, H., +, TMM 2021 4117-4130 Adversarial 3D Convolutional Auto-Encoder for Abnormal Event Detection in Videos.  ...  ., +, TMM 2021 1-11 Acoustics Acoustic Room Modelling Using 360 Stereo Cameras.  ... 
doi:10.1109/tmm.2022.3141947 fatcat:lil2nf3vd5ehbfgtslulu7y3lq

Table of Contents

2020 IEEE Signal Processing Letters  
Hasna 1295 Primary Quantization Matrix Estimation of Double Compressed JPEG Images via CNN . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .  ...  Shi 810 On Recoverability of Randomly Compressed Tensors With Low CP Rank . . . . . . . . . . . . . . . . .S. Ibrahim, X. Fu, and X.  ...  Xu 1899 Quantizing Oriented Object Detection Network via Outlier-Aware Quantization and IoU Approximation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .  ... 
doi:10.1109/lsp.2020.3040844 fatcat:xpovskhrvfgctk3hhufuvpyyne
« Previous Showing results 1 — 15 out of 245 results