Summary Classification of ambulance siren sound with MFCC-SVM - NASA/ADS ui.adsabs.harvard.edu
538 words - html page - View html page
One Line
The paper proposes using the MFCC-SVM approach to classify ambulance siren sounds and enhance the traffic light system's response to emergency vehicles.
Slides
Slide Presentation (12 slides)
Key Points
- Ambulance siren sound classification with MFCC-SVM
- Development of an embedded machine learning application
- Classifier for distinguishing "Ambulance Arrive" and "No Ambulance Arrive"
- Use in traffic light system to monitor ambulance arrival
- Approach based on Mel-frequency cepstral coefficients-Support Vector Machine (MFCC-SVM)
Summaries
25 word summary
This paper discusses using the MFCC-SVM approach to classify ambulance siren sounds. The goal is to improve the traffic light system's response to emergency vehicles.
42 word summary
This paper focuses on the classification of ambulance siren sounds using the MFCC-SVM approach. The goal is to develop a machine learning application that can accurately identify ambulance sirens in order to improve the traffic light system's response to emergency vehicles. The
Raw indexed text (3,798 chars / 538 words / 151 lines)
Classification of ambulance siren sound with MFCC-SVM - NASA/ADS
Skip to main content
Now on article abstract page
Toggle navigation
ads
Feedback
Submit Updates
General Feedback
ORCID
Sign in to ORCID to claim papers in the ADS.
About
About ADS
What's New
ADS Blog
ADS Help Pages
ADS Legacy Services
Careers@ADS
Sign Up
Log In
Our regular weekend ingest of new astronomy papers will be delayed by up to 3 days this week, due to server room maintenance. myADS emails will be sent once the work is completed.
Close
Search Bar to Enter New Query
quick field:
Author
First Author
Abstract
Year
Fulltext
Select a field or operator
abstract
abstract only
acknowledgements
affiliation
arXiv category
author count
author
bibcode
bibliographic group
bib abbrev, e.g. ApJ
body of article
data archive
collection
citation count
doctype
doi
entdate
first author
fulltext
identifier
inst
keyword
object
orcid
page
property
publication full name
date published
title
volume
year
citations()
pos()
references()
reviews()
similar()
topn()
trending()
useful()
single wildcard: ?
wildcard: *
exact match: =
All Search Terms
Your search returned 0 results
Your search returned
results
Show Menu
Full Text Sources
view
Abstract
Citations
References
Co-Reads
Similar Papers
Volume Content
Graphics
Metrics
Export Citation
Feedback
Classification of ambulance siren sound with MFCC-SVM
Show affiliations
Loading affiliations
affiliations loading
Suhaimy, Muhammad Afiq
Halim, Ili Shairah Abdul
Hassan, Siti Lailatul Mohd
Saparon, Azilah
Abstract
In both pattern recognition and artificial intelligence, audio identification has very broad theoretical and practical values. The noise from the surrounding area such as transportation, weather, and people's action affected the interruption in signal processing. Current traffic light system is lack of information when a vehicle is in emergencies such as ambulance, firefighter, and police. This paper is designed to develop an embedded machine learning application, including data acquisition, extraction of features, exploration of different algorithms, tuning for a good performance model and deploying the model in a simulation application. Specifically, a classifier of ambulance siren sound into `Ambulance Arrive' and `No Ambulance Arrive' has been developed, which could be used in the traffic light system to monitor the arrival of an ambulance which in an emergency. This paper suggests an approach based on Mel-frequency cepstral coefficients-Support Vector Machine (MFCC-SVM) on MATLAB R2017b tools that take advantage of the effect of feature representation and learner optimization tasks to effectively distinguish audio events from audio signals.
Publication:
AIP Conference Proceedings, Volume 2306, Issue 1, article id.020032
Pub Date:
December 2020
DOI:
10.1063/5.0032392
Bibcode:
2020AIPC.2306b0032S
Copied!
Feedback/Corrections?
full text sources
Publisher
Electronic on-line publisher article (HTML)
The SAO/NASA Astrophysics Data System
adshelp[at]cfa.harvard.edu
The ADS is operated by the Smithsonian Astrophysical Observatory under
NASA Cooperative Agreement
80NSSC21M0056
Resources
About ADS
ADS Help
What's New
Careers@ADS
Accessibility
Social
@adsabs
ADS Blog
Project
Switch to basic HTML
Privacy Policy
Terms of Use
Smithsonian Astrophysical Observatory
Smithsonian Institution
NASA
Back
How may we help you?
Missing/Incorrect Record
Submit a missing record or correct an existing record.
Missing References
Submit missing references to an existing ADS record.
Associated Articles
Submit associated articles to an existing record (e.g. arXiv /
published paper).
General Feedback
Send your comments and suggestions for improvements.
Name
Email
Feedback
Submit
You can also reach us at
adshelp [at] cfa.harvard.edu
Close without submitting
Alert