Modulation features for 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	2014-03-01T02:42:08Z
dc.date.available	2014-03-01T02:42:08Z
dc.date.issued	2002	en
dc.identifier.issn	07367791	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/30805
dc.subject	Automatic Speech Recognition	en
dc.subject	Robust Method	en
dc.subject	Speech Analysis	en
dc.subject	Speech Production	en
dc.subject	Speech Recognition	en
dc.subject	Word Recognition	en
dc.subject	Time Varying	en
dc.subject.other	Acoustic signal processing	en
dc.subject.other	Algorithms	en
dc.subject.other	Amplitude modulation	en
dc.subject.other	Database systems	en
dc.subject.other	Feature extraction	en
dc.subject.other	Frequency modulation	en
dc.subject.other	Markov processes	en
dc.subject.other	Mathematical models	en
dc.subject.other	Speech analysis	en
dc.subject.other	Automatic speech recognition systems	en
dc.subject.other	Hidden Markov models	en
dc.subject.other	Speech signals	en
dc.subject.other	Time varying models	en
dc.subject.other	Speech recognition	en
dc.title	Modulation features for speech recognition	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1109/ICASSP.2002.5743733	en
heal.identifier.secondary	http://dx.doi.org/10.1109/ICASSP.2002.5743733	en
heal.publicationDate	2002	en
heal.abstract	Automatic speech recognition (ASR) systems can benefit from including into their acoustic processing part new features that account for various nonlinear and time-varying phenomena during speech production. In this paper, we develop robust methods to extract novel acoustic features from speech signals of the modulation type based on time-varying models for speech analysis. Further, we integrate the new speech features with the standard linear ones (melfrequency cesptrum) to develop a augmented set of acoustic features and demonstrate its efficacy by showing significant improvements in HMM-based word recognition over the TIMIT database.	en
heal.journalName	ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings	en
dc.identifier.doi	10.1109/ICASSP.2002.5743733	en
dc.identifier.volume	1	en
dc.identifier.spage	I/377	en
dc.identifier.epage	I/380	en