Spectro-temporal features for howling frequency detection

Jae Won Lee, Seung Ho Choi

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

Abstract

The howling varies depending on the room environment and it is difficult to predict the howling. In this research work, we develop spectro-temporal features for howling frequency detection. For the detection of howling frequency, several techniques have been developed such as least mean square method. The proposed approach is based on statistical properties of temporal power spectra, which requires less computational complexity than conventional methods. The proposed method is experimentally shown to be suitable for applications in sound systems.

Original languageEnglish
Title of host publicationComputer Applications for Web, Human Computer Interaction, Signal and Image Processing, and Pattern Recognition - Int. Conf., SIP, WSE, and ICHCI 2012, Held in Conjunction with GST 2012, Proceedings
Pages25-30
Number of pages6
DOIs
StatePublished - 2012
Event2012 Int. Conf. on Signal Processing, Image Processing and Pattern Recognition, SIP 2012, 2012 Int. Conf. on Web Science and Engineering, WSE 2012, and the 2012 Int. Conf. on Human Computer Interaction, ICHCI 2012, Held in Conjunction with GST 2012 - Jeju Island, Korea, Republic of
Duration: 28 Nov 20122 Dec 2012

Publication series

NameCommunications in Computer and Information Science
Volume342 CCIS
ISSN (Print)1865-0929

Conference

Conference2012 Int. Conf. on Signal Processing, Image Processing and Pattern Recognition, SIP 2012, 2012 Int. Conf. on Web Science and Engineering, WSE 2012, and the 2012 Int. Conf. on Human Computer Interaction, ICHCI 2012, Held in Conjunction with GST 2012
Country/TerritoryKorea, Republic of
CityJeju Island
Period28/11/122/12/12

Keywords

  • Acoustic feedback circuit
  • Howling frequency detection
  • Spectro-temporal feature

Fingerprint

Dive into the research topics of 'Spectro-temporal features for howling frequency detection'. Together they form a unique fingerprint.

Cite this