Auditory teager energy cepstrum coefficients for robust speech recognition

Dimitriadis, D; Maragos, P; Potamianos, A

dc.contributor.author	Dimitriadis, D	en
dc.contributor.author	Maragos, P	en
dc.contributor.author	Potamianos, A	en
dc.date.accessioned	2014-03-01T02:43:09Z
dc.date.available	2014-03-01T02:43:09Z
dc.date.issued	2005	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/31254
dc.relation.uri	http://www.scopus.com/inward/record.url?eid=2-s2.0-33745225159&partnerID=40&md5=fdcff3918c3ab9bb541dad7384cbe9cc	en
dc.relation.uri	http://cvsp.cs.ntua.gr/publications/confr/DimitriadisMaragosPotamianos_AuditTeagEnergCepstrumRobustSpeechRecogn_Interspeech2005.pdf	en
dc.relation.uri	http://www.telecom.tuc.gr/%7Epotam/preprints/conf/05_EURO_features.pdf	en
dc.relation.uri	http://www.isca-speech.org/archive/interspeech_2005/i05_3013.html	en
dc.relation.uri	http://www.informatik.uni-trier.de/~ley/db/conf/interspeech/interspeech2005.html#DimitriadisMP05	en
dc.subject	Additive Noise	en
dc.subject	Feature Extraction	en
dc.subject	Human Auditory Processing	en
dc.subject	Speech Recognition	en
dc.subject	Error Rate	en
dc.subject	Mel Frequency Cepstrum Coefficient	en
dc.subject	Word Error Rate	en
dc.subject.other	Acoustic noise	en
dc.subject.other	Computational linguistics	en
dc.subject.other	Error analysis	en
dc.subject.other	Feature extraction	en
dc.subject.other	Magnetic resonance	en
dc.subject.other	Natural frequencies	en
dc.subject.other	Speech recognition	en
dc.subject.other	Energy cepstrum coefficients	en
dc.subject.other	Phone recognition tasks	en
dc.subject.other	Recording conditions	en
dc.subject.other	Teager Energy Cepstrum Coefficients (TECC)	en
dc.subject.other	Learning algorithms	en
dc.title	Auditory teager energy cepstrum coefficients for robust speech recognition	en
heal.type	conferenceItem	en
heal.publicationDate	2005	en
heal.abstract	In this paper, a feature extraction algorithm for robust speech recognition is introduced. The feature extraction algorithm is motivated by the human auditory processing and the nonlinear Teager-Kaiser energy operator that estimates the true energy of the source of a resonance. The proposed features are labeled as Teager Energy Cepstrum Coefficients (TECCs). TECCs are computed by first filtering the speech signal through a dense non constant-Q Gammatone filterbank and then by estimating the ""true"" energy of the signal's source, i.e., the short-time average of the output of the Teager-Kaiser energy operator. Error analysis and speech recognition experiments show that the TECCs and the mel frequency cepstrum coefficients (MFCCs) perform similarly for clean recording conditions; while the TECCs perform significantly better than the MFCCs for noisy recognition tasks. Specifically, relative word error rate improvement of 60% over the MFCC baseline is shown for the Aurora-3 database for the high-mismatch condition. Absolute error rate improvement ranging from 5% to 20% is shown for a phone recognition task in (various types of additive) noise.	en
heal.journalName	9th European Conference on Speech Communication and Technology	en
dc.identifier.spage	3013	en
dc.identifier.epage	3016	en