Advanced front-end for robust speech recognition in extremely adverse environments

Dimitriadis, D; Segura, JC; Garcia, L; Potamianos, A; Maragos, P; Pitsikalis, V

dc.contributor.author	Dimitriadis, D	en
dc.contributor.author	Segura, JC	en
dc.contributor.author	Garcia, L	en
dc.contributor.author	Potamianos, A	en
dc.contributor.author	Maragos, P	en
dc.contributor.author	Pitsikalis, V	en
dc.date.accessioned	2014-03-01T02:44:25Z
dc.date.available	2014-03-01T02:44:25Z
dc.date.issued	2007	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/31815
dc.relation.uri	http://www.scopus.com/inward/record.url?eid=2-s2.0-56149121417&partnerID=40&md5=2365354c3801c3b3075fed110101be2a	en
dc.relation.uri	http://www.telecom.tuc.gr/%7Epotam/preprints/conf/07_intespeech_HAFE.pdf	en
dc.relation.uri	http://cvsp.cs.ntua.gr/projects/pub/HIWIRE/HiwirePublications/DMSP_HAFE_ASR_Interspeech07.pdf	en
dc.relation.uri	http://www.isca-speech.org/archive/interspeech_2007/i07_2425.html	en
dc.relation.uri	http://www.informatik.uni-trier.de/~ley/db/conf/interspeech/interspeech2007.html#DimitriadisSGPMP07	en
dc.subject	Noise invariant features	en
dc.subject	Noise suppression	en
dc.subject	Nonlinear features	en
dc.subject	Parameter equalization	en
dc.subject	Speech recognition	en
dc.subject.other	Feature extraction	en
dc.subject.other	Modulation	en
dc.subject.other	Speech	en
dc.subject.other	Speech analysis	en
dc.subject.other	Speech enhancement	en
dc.subject.other	Speech recognition	en
dc.subject.other	Activity detections	en
dc.subject.other	Adverse environments	en
dc.subject.other	Error rate reductions	en
dc.subject.other	Feature normalizations	en
dc.subject.other	Fractal features	en
dc.subject.other	Frontend	en
dc.subject.other	Invariant features	en
dc.subject.other	Noise invariant features	en
dc.subject.other	Noise suppression	en
dc.subject.other	Nonlinear features	en
dc.subject.other	Nonlinear modulations	en
dc.subject.other	Parameter equalization	en
dc.subject.other	Processing modules	en
dc.subject.other	Recognition rates	en
dc.subject.other	Robust speech recognitions	en
dc.subject.other	Unified approaches	en
dc.subject.other	Wiener filtering	en
dc.subject.other	Speech communication	en
dc.title	Advanced front-end for robust speech recognition in extremely adverse environments	en
heal.type	conferenceItem	en
heal.publicationDate	2007	en
heal.abstract	In this paper, a unified approach to speech enhancement, feature extraction and feature normalization for speech recognition in adverse recording conditions is presented. The proposed frontend system consists of several different, independent, processing modules. Each of the algorithms contained in these modules has been independently applied to the problem of speech recognition in noise, significantly improving the recognition rates. In this work, these algorithms are merged in a single front-end and their combined performance is demonstrated. Specifically, the proposed advanced front-end extracts noise-invariant features via the following modules: Wiener filtering, voice-activity detection, robust feature extraction (nonlinear modulation or fractal features), parameter equalization and frame-dropping. The advanced front-end is applied to extremely adverse environments where most feature extraction schemes fail. We show that by combining speech enhancement, robust feature extraction and feature normalization up to a fivefold error rate reduction can be achieved for certain tasks.	en
heal.journalName	International Speech Communication Association - 8th Annual Conference of the International Speech Communication Association, Interspeech 2007	en
dc.identifier.volume	3	en
dc.identifier.spage	2221	en
dc.identifier.epage	2224	en