Sound analysis in smart cities

Juan Bello, Charlie Mydlarz, Justin Salamon

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

This chapter introduces the concept of smart cities and discusses the importance of sound as a source of information about urban life. It describes a wide range of applications for the computational analysis of urban sounds and focuses on two high-impact areas, audio surveillance, and noise pollution monitoring, which sit at the intersection of dense sensor networks and machine listening. For sensor networks we focus on the pros and cons of mobile versus static sensing strategies, and the description of a low-cost solution to acoustic sensing that supports distributed machine listening. For sound event detection and classification we focus on the challenges presented by this task, solutions including feature design and learning strategies, and how a combination of convolutional networks and data augmentation result in the current state of the art. We close with a discussion about the potential and challenges of mobile sensing, the limitations imposed by the data currently available for research, and a few areas for future exploration.

Original languageEnglish (US)
Title of host publicationComputational Analysis of Sound Scenes and Events
PublisherSpringer International Publishing
Pages373-397
Number of pages25
ISBN (Electronic)9783319634500
ISBN (Print)9783319634494
DOIs
StatePublished - Sep 21 2017

Fingerprint

Acoustic waves
Sensor networks
acoustics
Noise pollution
pollution monitoring
noise pollution
sensors
surveillance
Acoustics
intersections
learning
Monitoring
Smart city
augmentation
Costs

Keywords

  • Acoustic sensing
  • Audio surveillance
  • Convolutional neural networks
  • Data augmentation
  • Deep learning
  • Internet of things (IOT)
  • Machine learning
  • Machine listening
  • MEMS microphone
  • Noise monitoring
  • Sensor network
  • Smart cities
  • Sound classification
  • Sound event detection
  • Urban sound

ASJC Scopus subject areas

  • Engineering(all)
  • Physics and Astronomy(all)
  • Computer Science(all)

Cite this

Bello, J., Mydlarz, C., & Salamon, J. (2017). Sound analysis in smart cities. In Computational Analysis of Sound Scenes and Events (pp. 373-397). Springer International Publishing. https://doi.org/10.1007/978-3-319-63450-0_13

Sound analysis in smart cities. / Bello, Juan; Mydlarz, Charlie; Salamon, Justin.

Computational Analysis of Sound Scenes and Events. Springer International Publishing, 2017. p. 373-397.

Research output: Chapter in Book/Report/Conference proceedingChapter

Bello, J, Mydlarz, C & Salamon, J 2017, Sound analysis in smart cities. in Computational Analysis of Sound Scenes and Events. Springer International Publishing, pp. 373-397. https://doi.org/10.1007/978-3-319-63450-0_13
Bello J, Mydlarz C, Salamon J. Sound analysis in smart cities. In Computational Analysis of Sound Scenes and Events. Springer International Publishing. 2017. p. 373-397 https://doi.org/10.1007/978-3-319-63450-0_13
Bello, Juan ; Mydlarz, Charlie ; Salamon, Justin. / Sound analysis in smart cities. Computational Analysis of Sound Scenes and Events. Springer International Publishing, 2017. pp. 373-397
@inbook{1ef8c7b797b74e24b53cff080e72a209,
title = "Sound analysis in smart cities",
abstract = "This chapter introduces the concept of smart cities and discusses the importance of sound as a source of information about urban life. It describes a wide range of applications for the computational analysis of urban sounds and focuses on two high-impact areas, audio surveillance, and noise pollution monitoring, which sit at the intersection of dense sensor networks and machine listening. For sensor networks we focus on the pros and cons of mobile versus static sensing strategies, and the description of a low-cost solution to acoustic sensing that supports distributed machine listening. For sound event detection and classification we focus on the challenges presented by this task, solutions including feature design and learning strategies, and how a combination of convolutional networks and data augmentation result in the current state of the art. We close with a discussion about the potential and challenges of mobile sensing, the limitations imposed by the data currently available for research, and a few areas for future exploration.",
keywords = "Acoustic sensing, Audio surveillance, Convolutional neural networks, Data augmentation, Deep learning, Internet of things (IOT), Machine learning, Machine listening, MEMS microphone, Noise monitoring, Sensor network, Smart cities, Sound classification, Sound event detection, Urban sound",
author = "Juan Bello and Charlie Mydlarz and Justin Salamon",
year = "2017",
month = "9",
day = "21",
doi = "10.1007/978-3-319-63450-0_13",
language = "English (US)",
isbn = "9783319634494",
pages = "373--397",
booktitle = "Computational Analysis of Sound Scenes and Events",
publisher = "Springer International Publishing",

}

TY - CHAP

T1 - Sound analysis in smart cities

AU - Bello, Juan

AU - Mydlarz, Charlie

AU - Salamon, Justin

PY - 2017/9/21

Y1 - 2017/9/21

N2 - This chapter introduces the concept of smart cities and discusses the importance of sound as a source of information about urban life. It describes a wide range of applications for the computational analysis of urban sounds and focuses on two high-impact areas, audio surveillance, and noise pollution monitoring, which sit at the intersection of dense sensor networks and machine listening. For sensor networks we focus on the pros and cons of mobile versus static sensing strategies, and the description of a low-cost solution to acoustic sensing that supports distributed machine listening. For sound event detection and classification we focus on the challenges presented by this task, solutions including feature design and learning strategies, and how a combination of convolutional networks and data augmentation result in the current state of the art. We close with a discussion about the potential and challenges of mobile sensing, the limitations imposed by the data currently available for research, and a few areas for future exploration.

AB - This chapter introduces the concept of smart cities and discusses the importance of sound as a source of information about urban life. It describes a wide range of applications for the computational analysis of urban sounds and focuses on two high-impact areas, audio surveillance, and noise pollution monitoring, which sit at the intersection of dense sensor networks and machine listening. For sensor networks we focus on the pros and cons of mobile versus static sensing strategies, and the description of a low-cost solution to acoustic sensing that supports distributed machine listening. For sound event detection and classification we focus on the challenges presented by this task, solutions including feature design and learning strategies, and how a combination of convolutional networks and data augmentation result in the current state of the art. We close with a discussion about the potential and challenges of mobile sensing, the limitations imposed by the data currently available for research, and a few areas for future exploration.

KW - Acoustic sensing

KW - Audio surveillance

KW - Convolutional neural networks

KW - Data augmentation

KW - Deep learning

KW - Internet of things (IOT)

KW - Machine learning

KW - Machine listening

KW - MEMS microphone

KW - Noise monitoring

KW - Sensor network

KW - Smart cities

KW - Sound classification

KW - Sound event detection

KW - Urban sound

UR - http://www.scopus.com/inward/record.url?scp=85035036085&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85035036085&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-63450-0_13

DO - 10.1007/978-3-319-63450-0_13

M3 - Chapter

SN - 9783319634494

SP - 373

EP - 397

BT - Computational Analysis of Sound Scenes and Events

PB - Springer International Publishing

ER -