Acoustic event classification using graph signals

Manjunath Mulimani, U. P. Jahnavi, Shashidhar G. Koolagudi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

7 Citations (Scopus)

Abstract

In this paper, a graph signal is generated from spectrogram and features are investigated from graph signal for Acoustic Event Classification (AEC). Different acoustic events are selected from Sound Scene Database of Real Word Computing Partnership (RWCP) group. Three different noises are selected from NOISEX'92 database and added to test samples at different noise conditions separately. The recognition performance of acoustic events using proposed features and Mel-frequency cepstral coefficients (MFCCs) with clean and noisy test samples are compared. The proposed features show significantly improved recognition accuracy over MFCCs in noisy conditions.

Original languageEnglish
Title of host publicationTENCON 2017 - 2017 IEEE Region 10 Conference
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1812-1816
Number of pages5
ISBN (Electronic)9781509011339
DOIs
Publication statusPublished - 19-12-2017
Event2017 IEEE Region 10 Conference, TENCON 2017 - Penang, Malaysia
Duration: 05-11-201708-11-2017

Publication series

NameIEEE Region 10 Annual International Conference, Proceedings/TENCON
Volume2017-December
ISSN (Print)2159-3442
ISSN (Electronic)2159-3450

Conference

Conference2017 IEEE Region 10 Conference, TENCON 2017
Country/TerritoryMalaysia
CityPenang
Period05-11-1708-11-17

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Acoustic event classification using graph signals'. Together they form a unique fingerprint.

Cite this