Single-channel noise reduction in the STFT domain from the fullband output SNR perspective

Yingke Zhao, Jacob Benesty, Jingdong Chen

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

1 Scopus citations

Abstract

This paper develops a single-channel noise reduction algorithm in the short-time Fourier transform (STFT) domain, which attempts to optimize the fullband output signal-to-noise ratio (SNR). We show that the conventionalWiener filter, the maximum SNR filter, and the ideal binary mask based method are particular cases of the developed algorithm. Simulations are presented to illustrate the properties of this algorithm.

Original languageEnglish
Title of host publication2016 24th European Signal Processing Conference, EUSIPCO 2016
PublisherEuropean Signal Processing Conference, EUSIPCO
Pages1956-1959
Number of pages4
ISBN (Electronic)9780992862657
DOIs
StatePublished - 28 Nov 2016
Event24th European Signal Processing Conference, EUSIPCO 2016 - Budapest, Hungary
Duration: 28 Aug 20162 Sep 2016

Publication series

NameEuropean Signal Processing Conference
Volume2016-November
ISSN (Print)2219-5491

Conference

Conference24th European Signal Processing Conference, EUSIPCO 2016
Country/TerritoryHungary
CityBudapest
Period28/08/162/09/16

Keywords

  • Fullband output SNR
  • Ideal binary mask
  • Noise reduction
  • Optimal gains
  • Speech enhancement
  • STFT domain

Fingerprint

Dive into the research topics of 'Single-channel noise reduction in the STFT domain from the fullband output SNR perspective'. Together they form a unique fingerprint.

Cite this