Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/101329
Full metadata record
DC FieldValueLanguage
dc.contributor.authorKhoa, Pham Chauen
dc.contributor.authorSiong, Chng Engen
dc.date.accessioned2013-10-04T06:29:46Zen
dc.date.accessioned2019-12-06T20:36:48Z-
dc.date.available2013-10-04T06:29:46Zen
dc.date.available2019-12-06T20:36:48Z-
dc.date.copyright2012en
dc.date.issued2012en
dc.identifier.citationKhoa, P. C., & Siong, C. E. (2012). Spectral local harmonicity feature for voice activity detection. 2012 International Conference on Audio, Language and Image Processing (ICALIP).en
dc.identifier.urihttps://hdl.handle.net/10356/101329-
dc.identifier.urihttp://hdl.handle.net/10220/16271en
dc.description.abstractIn this paper, we propose a method to exploit the harmonicity of human voiced speech using only the most harmonic sub-part of the spectrum. This technique searches for all the potential sub-windows of the spectrum, and measures their local harmonicity, using a newly proposed metric, which works in the spectral autocorrelation domain and employs a novel sinusoidal fitting approach. Experiments show that the new feature can be used to detect noisy voiced speech frames heavily corrupted by non-stationary noise even at 0dB SNR with high precision and recall, which gives better results than the Windowed Autocorrelation Lag Energy (WALE), a recently proposed voicing features, under a complex factory noise scenarios.en
dc.language.isoenen
dc.subjectDRNTU::Engineering::Computer science and engineeringen
dc.titleSpectral local harmonicity feature for voice activity detectionen
dc.typeConference Paperen
dc.contributor.schoolSchool of Computer Engineeringen
dc.contributor.conferenceInternational Conference on Audio, Language and Image Processing (2012 : Shanghai, China)en
dc.contributor.researchTemasek Laboratoriesen
dc.identifier.doihttp://dx.doi.org/10.1109/ICALIP.2012.6376652en
item.grantfulltextnone-
item.fulltextNo Fulltext-
Appears in Collections:TL Conference Papers

Google ScholarTM

Check

Altmetric

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.