Single-channel transient interference suppression with diffusion maps

Ronen Talmon, Israel Cohen, Sharon Gannot

Research output: Contribution to journalArticlepeer-review

38 Scopus citations

Abstract

A transient is an abrupt or impulsive sound followed by decaying oscillations, e.g., keyboard typing and door knocking. Such sounds often arise as interference in everyday applications, e.g., hearing aids, hands-free accessories, mobile phones, and conference-room devices. In this paper, we present an algorithm for single-channel transient interference suppression. The main component of the proposed algorithm is the estimation of the spectral variance of the interference. We propose a statistical model of the transient interference and combine it with non-local filtering. We exploit the unique spectral structure of the transients along with their impulsive temporal nature to distinct them from speech. A particular attention is given to handling both short-and long-duration transients. Experimental results show that the proposed algorithm enables significant transient suppression for a variety of transient types.

Original languageEnglish
Article number6287556
Pages (from-to)132-144
Number of pages13
JournalIEEE Transactions on Audio, Speech and Language Processing
Volume21
Issue number1
DOIs
StatePublished - 2013

Keywords

  • Speech enhancement
  • acoustic noise
  • impulse noise
  • speech processing
  • transient noise

Fingerprint

Dive into the research topics of 'Single-channel transient interference suppression with diffusion maps'. Together they form a unique fingerprint.

Cite this