Continuous energy demodulation methods and application to speech analysis

Dimitriadis, D; Maragos, P

dc.contributor.author	Dimitriadis, D	en
dc.contributor.author	Maragos, P	en
dc.date.accessioned	2014-03-01T01:23:44Z
dc.date.available	2014-03-01T01:23:44Z
dc.date.issued	2006	en
dc.identifier.issn	0167-6393	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/17122
dc.subject	AM-FM modulations	en
dc.subject	ASR	en
dc.subject	Demodulation	en
dc.subject	Energy operators	en
dc.subject	Feature distributions	en
dc.subject	Gabor filterbanks	en
dc.subject	Nonlinear speech analysis	en
dc.subject	Nonstationary speech analysis	en
dc.subject	Robust features	en
dc.subject.classification	Acoustics	en
dc.subject.classification	Communication	en
dc.subject.classification	Computer Science, Interdisciplinary Applications	en
dc.subject.classification	Language & Linguistics	en
dc.subject.other	Approximation theory	en
dc.subject.other	Frequency modulation	en
dc.subject.other	Mathematical operators	en
dc.subject.other	Signal processing	en
dc.subject.other	Splines	en
dc.subject.other	Statistical methods	en
dc.subject.other	AM-FM modulations	en
dc.subject.other	Energy operators	en
dc.subject.other	Gabor filterbanks	en
dc.subject.other	Nonlinear speech analysis	en
dc.subject.other	Nonstationary speech analysis	en
dc.subject.other	Demodulation	en
dc.title	Continuous energy demodulation methods and application to speech analysis	en
heal.type	journalArticle	en
heal.identifier.primary	10.1016/j.specom.2005.08.007	en
heal.identifier.secondary	http://dx.doi.org/10.1016/j.specom.2005.08.007	en
heal.language	English	en
heal.publicationDate	2006	en
heal.abstract	Speech resonance signals appear to contain significant amplitude and frequency modulations. An efficient demodulation approach is based on energy operators. In this paper, we develop two new robust methods for energy-based speech demodulation and compare their performance on both test and actual speech signals. The first method uses smoothing splines for discrete-to-continuous signal approximation. The second (and best) method uses time-derivatives of Gabor filters. Further, we apply the best demodulation method to explore the statistical distribution of speech modulation features and study their properties regarding applications of speech classification and recognition. Finally, we present some preliminary recognition results and underline their improvements when compared to the corresponding MFCC results. (C) 2005 Elsevier B.V. All rights reserved.	en
heal.publisher	ELSEVIER SCIENCE BV	en
heal.journalName	Speech Communication	en
dc.identifier.doi	10.1016/j.specom.2005.08.007	en
dc.identifier.isi	ISI:000239178600005	en
dc.identifier.volume	48	en
dc.identifier.issue	7	en
dc.identifier.spage	819	en
dc.identifier.epage	837	en