Multiband, multisensor robust features for noisy speech recognition

Dimitriadis, D; Maragos, P; Lefkimmiatis, S

dc.contributor.author	Dimitriadis, D	en
dc.contributor.author	Maragos, P	en
dc.contributor.author	Lefkimmiatis, S	en
dc.date.accessioned	2014-03-01T02:44:50Z
dc.date.available	2014-03-01T02:44:50Z
dc.date.issued	2007	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/31970
dc.relation.uri	http://www.scopus.com/inward/record.url?eid=2-s2.0-56149090724&partnerID=40&md5=d956ef94dce7481763eb5f475ea1a974	en
dc.relation.uri	http://cvsp.cs.ntua.gr/projects/bin/viewfile/HIWIRE/HiwirePublications?rev=1	en
dc.relation.uri	filename=DML_MaxTECC_ASR_InterSpeech07.pdf	en
dc.relation.uri	http://cvsp.cs.ntua.gr/publications/confr/DimitriadisMaragosLefkimmiatis_MinTECCASR_InterSpeech07.pdf	en
dc.relation.uri	http://cvsp.cs.ntua.gr/projects/pub/HIWIRE/HiwirePublications/DML_MaxTECC_ASR_InterSpeech07.pdf	en
dc.relation.uri	http://www.isca-speech.org/archive/interspeech_2007/i07_0246.html	en
dc.relation.uri	http://www.informatik.uni-trier.de/~ley/db/conf/interspeech/interspeech2007.html#DimitriadisML07	en
dc.subject	Modulations	en
dc.subject	Multiband processing	en
dc.subject	Multisensor array	en
dc.subject	Robust features	en
dc.subject	Speech recognition	en
dc.subject.other	Feature extraction	en
dc.subject.other	Flow of fluids	en
dc.subject.other	Frequency bands	en
dc.subject.other	Ketones	en
dc.subject.other	Modulation	en
dc.subject.other	Sensor arrays	en
dc.subject.other	Speech	en
dc.subject.other	Speech analysis	en
dc.subject.other	Speech recognition	en
dc.subject.other	Cepstral	en
dc.subject.other	Different frequencies	en
dc.subject.other	MFCC features	en
dc.subject.other	Multiband	en
dc.subject.other	Multiband processing	en
dc.subject.other	Multiple frequencies	en
dc.subject.other	Multisensor	en
dc.subject.other	Multisensor array	en
dc.subject.other	Multisensor arrays	en
dc.subject.other	Multisensor environments	en
dc.subject.other	Noise energies	en
dc.subject.other	Noise signals	en
dc.subject.other	Noisy speech recognitions	en
dc.subject.other	Nonlinear modulations	en
dc.subject.other	Recognition performances	en
dc.subject.other	Robust features	en
dc.subject.other	Spatial diversities	en
dc.subject.other	Speech models	en
dc.subject.other	Speech signals	en
dc.subject.other	Speech communication	en
dc.title	Multiband, multisensor robust features for noisy speech recognition	en
heal.type	conferenceItem	en
heal.publicationDate	2007	en
heal.abstract	This paper presents a novel feature extraction scheme taking advantage of both the nonlinear modulation speech model and the spatial diversity of speech and noise signals in a multisensor environment. Herein, we propose applying robust features to speech signals captured by a multisensor array minimizing a noise energy criterion over multiple frequency bands. We show that we can achieve improved recognition performance by minimizing the Teager-Kaiser energy of the noisecorrupted signals in different frequency bands. These Multi-band, Multisensor Cepstral (MBSC) features are inspired by similar ones already been applied to single-microphone noisy Speech Recognition tasks with significantly improved results. The recognition results show that the proposed features can perform better than the widely-used MFCC features.	en
heal.journalName	International Speech Communication Association - 8th Annual Conference of the International Speech Communication Association, Interspeech 2007	en
dc.identifier.volume	2	en
dc.identifier.spage	889	en
dc.identifier.epage	892	en