Skip to main navigation Skip to search Skip to main content

Transient interference suppression in speech signals based on the OM-LSA algorithm

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

Abstract

Typical transient interferences, e.g. door knocks and keyboard tapping, are short in time, widely spread across the frequency domain, and have an abrupt nature. Thus, traditional speech enhancement techniques that use temporal smoothing to estimate the power spectral density (PSD) of the interference are inadequate. In this paper, we present a speech enhancement algorithm that suppresses transient interferences and pseudo-stationary background noise. The algorithm comprises an estimation of the transient and the pseudo-stationary noise PSDs, and enhancement of speech. The proposed algorithm is capable of tracking rapid variations of the input signal spectra and enables to effectively estimate the PSD of the transients. Experimental results show that the proposed algorithm is robust, does not rely on transient periodicity or reoccurrence, and exhibits good performance for various transient interference types.

Original languageEnglish GB
Title of host publicationInternational Workshop on Acoustic Signal Enhancement, IWAENC 2012
ISBN (Electronic)9783800734511
StatePublished - 2012
EventInternational Workshop on Acoustic Signal Enhancement, IWAENC 2012 - Aachen, Germany
Duration: 4 Sep 20126 Sep 2012

Publication series

NameInternational Workshop on Acoustic Signal Enhancement, IWAENC 2012

Conference

ConferenceInternational Workshop on Acoustic Signal Enhancement, IWAENC 2012
Country/TerritoryGermany
CityAachen
Period4/09/126/09/12

Keywords

  • Acoustic noise
  • Impulse noise
  • Speech enhancement
  • Speech processing
  • Transient noise

ASJC Scopus subject areas

  • Software
  • Acoustics and Ultrasonics
  • Computer Networks and Communications
  • Signal Processing

Fingerprint

Dive into the research topics of 'Transient interference suppression in speech signals based on the OM-LSA algorithm'. Together they form a unique fingerprint.

Cite this