Transformers for Urban Sound Classification—A Comprehensive Performance Evaluation

Author:

Nogueira Ana Filipa RodriguesORCID,Oliveira Hugo S.ORCID,Machado José J. M.ORCID,Tavares João Manuel R. S.ORCID

Abstract

Many relevant sound events occur in urban scenarios, and robust classification models are required to identify abnormal and relevant events correctly. These models need to identify such events within valuable time, being effective and prompt. It is also essential to determine for how much time these events prevail. This article presents an extensive analysis developed to identify the best-performing model to successfully classify a broad set of sound events occurring in urban scenarios. Analysis and modelling of Transformer models were performed using available public datasets with different sets of sound classes. The Transformer models’ performance was compared to the one achieved by the baseline model and end-to-end convolutional models. Furthermore, the benefits of using pre-training from image and sound domains and data augmentation techniques were identified. Additionally, complementary methods that have been used to improve the models’ performance and good practices to obtain robust sound classification models were investigated. After an extensive evaluation, it was found that the most promising results were obtained by employing a Transformer model using a novel Adam optimizer with weight decay and transfer learning from the audio domain by reusing the weights from AudioSet, which led to an accuracy score of 89.8% for the UrbanSound8K dataset, 95.8% for the ESC-50 dataset, and 99% for the ESC-10 dataset, respectively.

Funder

the project Safe Cities—”Inovação para Construir Cidades Seguras”

the European Regional Development Fund

Publisher

MDPI AG

Subject

Electrical and Electronic Engineering,Biochemistry,Instrumentation,Atomic and Molecular Physics, and Optics,Analytical Chemistry

Cited by 6 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Graph-Based Audio Classification Using Pre-Trained Models and Graph Neural Networks;Sensors;2024-03-26

2. Invisible track bed defect classification method based on distributed optical fiber sensing system and FFT Attention Transformer model;Optical Engineering;2024-02-20

3. Cross-modal and Cross-medium Adversarial Attack for Audio;Proceedings of the 31st ACM International Conference on Multimedia;2023-10-26

4. Misophonia Sound Recognition Using Vision Transformer;2023 45th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC);2023-07-24

5. A Comparative Analysis of Image Captioning Techniques;2023 4th International Conference for Emerging Technology (INCET);2023-05-26

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3