Sound-event classification using pseudo-color CENTRIST feature and classifier selection

Jianfeng Ren, Xudong Jiang, Junsong Yuan

Research output: Chapter in Book/Conference proceedingConference contributionpeer-review

7 Citations (Scopus)

Abstract

Sound-event classification often extracts features from an image-like spectrogram. Recent approaches such as spectrogram image feature and subband-power-distribution image feature extract local statistics such as mean and variance from the spectrogram. We argue that such simple image statistics cannot well capture complex texture details of the spectrogram. Thus, we propose to extract pseudo-color CENTRIST features from the logarithm of Gammatone-like spectrogram. To well classify the sound event under the unknown noise condition, we propose a classifier-selection scheme, which automatically selects the most suitable classifier. The proposed approach is compared with the state of the art on the RWCP database, and demonstrates a superior performance.

Original languageEnglish
Title of host publicationFirst International Workshop on Pattern Recognition
EditorsXudong Jiang, Guojian Chen, Chiharu Ishii, Genci Capi
PublisherSPIE
ISBN (Electronic)9781510604308
DOIs
Publication statusPublished - 2016
Externally publishedYes
Event1st International Workshop on Pattern Recognition - Tokyo, Japan
Duration: 11 May 201613 May 2016

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume10011
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Conference

Conference1st International Workshop on Pattern Recognition
Country/TerritoryJapan
CityTokyo
Period11/05/1613/05/16

Keywords

  • Classifier Selection
  • Pseudo-Color CENTRIST Feature
  • Sound-Event Classification

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Sound-event classification using pseudo-color CENTRIST feature and classifier selection'. Together they form a unique fingerprint.

Cite this