File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Modifying the normalized covariance metric measure to account for nonlinear distortions introduced by noise-reduction algorithms

TitleModifying the normalized covariance metric measure to account for nonlinear distortions introduced by noise-reduction algorithms
Authors
KeywordsAdaptive thresholding
Gain-induced
Intelligibility scores
Noise-suppression algorithms
Normalized covariance
Issue Date2013
PublisherAcoustical Society of America. The Journal's web site is located at http://asa.aip.org/jasa.html
Citation
Journal of the Acoustical Society of America, 2013, v. 133 n. 5, p. EL405-EL411 How to Cite?
AbstractIn this study, two methods are proposed to modify the normalized covariance metric (NCM) measure to reduce the effects of gain-induced nonlinear distortions introduced by most noise-suppression algorithms. Considering that the gain-induced distortions behave differently dependent on the signal-to-noise ratio between the noise-reduced speech and the noise, the first approach introduces a penalty factor involving this ratio in the modified NCM measure. The second approach deemphasizes segments marked with amplification distortions that contribute less to intelligibility via adaptive thresholding. Significantly higher correlations with intelligibility scores were obtained from the modified NCM measures compared with the original NCM measures.
Persistent Identifierhttp://hdl.handle.net/10722/183164
ISSN
2023 Impact Factor: 2.1
2023 SCImago Journal Rankings: 0.687
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorChen, Fen_US
dc.contributor.authorHu, YIen_US
dc.date.accessioned2013-05-15T01:45:57Z-
dc.date.available2013-05-15T01:45:57Z-
dc.date.issued2013en_US
dc.identifier.citationJournal of the Acoustical Society of America, 2013, v. 133 n. 5, p. EL405-EL411-
dc.identifier.issn0001-4966-
dc.identifier.urihttp://hdl.handle.net/10722/183164-
dc.description.abstractIn this study, two methods are proposed to modify the normalized covariance metric (NCM) measure to reduce the effects of gain-induced nonlinear distortions introduced by most noise-suppression algorithms. Considering that the gain-induced distortions behave differently dependent on the signal-to-noise ratio between the noise-reduced speech and the noise, the first approach introduces a penalty factor involving this ratio in the modified NCM measure. The second approach deemphasizes segments marked with amplification distortions that contribute less to intelligibility via adaptive thresholding. Significantly higher correlations with intelligibility scores were obtained from the modified NCM measures compared with the original NCM measures.-
dc.languageengen_US
dc.publisherAcoustical Society of America. The Journal's web site is located at http://asa.aip.org/jasa.html-
dc.relation.ispartofJournal of the Acoustical Society of Americaen_US
dc.rightsCopyright 2013 Acoustical Society of America. This article may be downloaded for personal use only. Any other use requires prior permission of the author and the Acoustical Society of America. The following article appeared in Journal of the Acoustical Society of America, 2013, v. 133 n. 5, p. EL405-EL411 and may be found at https://doi.org/10.1121/1.4800189-
dc.subjectAdaptive thresholding-
dc.subjectGain-induced-
dc.subjectIntelligibility scores-
dc.subjectNoise-suppression algorithms-
dc.subjectNormalized covariance-
dc.titleModifying the normalized covariance metric measure to account for nonlinear distortions introduced by noise-reduction algorithmsen_US
dc.typeArticleen_US
dc.identifier.emailChen, F: feichen1@hku.hken_US
dc.identifier.emailHu, YI: huy@uwm.edu-
dc.identifier.authorityChen, FF=rp01593en_US
dc.description.naturepublished_or_final_version-
dc.identifier.doi10.1121/1.4800189-
dc.identifier.pmid23656101-
dc.identifier.scopuseid_2-s2.0-84877620930-
dc.identifier.hkuros219365en_US
dc.identifier.volume133en_US
dc.identifier.issue5-
dc.identifier.spageEL405en_US
dc.identifier.epageEL411en_US
dc.identifier.isiWOS:000318555900011-
dc.publisher.placeUnited States-
dc.identifier.issnl0001-4966-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats