A novel binary mask estimator based on sparse approximation

Abigail Anne Kressner, David V. Anderson, Christopher J. Rozell

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

Abstract

While most single-channel noise reduction algorithms fail to improve speech intelligibility, the ideal binary mask (IBM) has demonstrated substantial intelligibility improvements. However, this approach exploits oracle knowledge. The main objective of this paper is to introduce a novel binary mask estimator based on a simple sparse approximation algorithm. Our approach does not require oracle knowledge and instead uses knowledge of speech structure. © 2013 IEEE.
Original languageEnglish
Title of host publicationProceedings of Ieee International Conference on Acoustics, Speech and Signal Processing
PublisherIEEE
Publication date2013
Pages7497-7501
ISBN (Print)978-1-4799-0356-6
DOIs
Publication statusPublished - 2013
Externally publishedYes
EventIEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2013) - Vancouver, Canada
Duration: 26 May 201331 May 2013
http://www.icassp2013.com/

Conference

ConferenceIEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2013)
CountryCanada
CityVancouver
Period26/05/201331/05/2013
Internet address
SeriesI E E E International Conference on Acoustics, Speech and Signal Processing. Proceedings
ISSN1520-6149

Keywords

  • Signal Processing
  • Software
  • Electrical and Electronic Engineering
  • Ideal binary mask
  • intelligibility
  • noise reduction
  • sparse approximation
  • time-frequency masking
  • Binary masks
  • Ideal binary mask (IBM)
  • Intelligibility improvements
  • Single-channel noise reductions
  • Sparse approximations
  • Time-Frequency Masking
  • Approximation algorithms
  • Noise abatement
  • Signal processing
  • Speech intelligibility
  • Acoustic noise
  • approximation theory
  • speech intelligibility
  • Signal Processing and Analysis
  • Approximation methods
  • binary mask estimator
  • Matching pursuit algorithms
  • oracle knowledge
  • Signal processing algorithms
  • Signal to noise ratio
  • single-channel noise reduction algorithm
  • Speech
  • Time-frequency analysis

Fingerprint Dive into the research topics of 'A novel binary mask estimator based on sparse approximation'. Together they form a unique fingerprint.

Cite this