Time-frequency distributions for automatic speech recognition

Potamianos, A; Maragos, P

dc.contributor.author	Potamianos, A	en
dc.contributor.author	Maragos, P	en
dc.date.accessioned	2014-03-01T01:17:17Z
dc.date.available	2014-03-01T01:17:17Z
dc.date.issued	2001	en
dc.identifier.issn	10636676	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/14433
dc.subject	Speech analysis	en
dc.subject	Speech processing	en
dc.subject	Speech recognition	en
dc.subject	Time-frequency analysis	en
dc.subject.other	Bandpass filters	en
dc.subject.other	Markov processes	en
dc.subject.other	Mathematical operators	en
dc.subject.other	Speech analysis	en
dc.subject.other	Automatic speech recognition	en
dc.subject.other	Time-frequency distributions	en
dc.subject.other	Speech recognition	en
dc.title	Time-frequency distributions for automatic speech recognition	en
heal.type	journalArticle	en
heal.identifier.primary	10.1109/89.905994	en
heal.identifier.secondary	http://dx.doi.org/10.1109/89.905994	en
heal.publicationDate	2001	en
heal.abstract	The use of general time-frequency distributions as features for automatic speech recognition (ASR) is discussed in the context of hidden Markov classifiers. Short-time averages of quadratic operators, e.g., energy spectrum, generalized first spectral moments, and short-time averages of the instantaneous frequency, are compared to the standard front end features, and applied to ASR. Theoretical and experimental results indicate a close relationship among these feature sets.	en
heal.journalName	IEEE Transactions on Speech and Audio Processing	en
dc.identifier.doi	10.1109/89.905994	en
dc.identifier.volume	9	en
dc.identifier.issue	3	en
dc.identifier.spage	196	en
dc.identifier.epage	200	en