Short-time instantaneous frequency and bandwidth features for speech recognition

Tsiakoulis, P; Potamianos, A; Dimitriadis, D

dc.contributor.author	Tsiakoulis, P	en
dc.contributor.author	Potamianos, A	en
dc.contributor.author	Dimitriadis, D	en
dc.date.accessioned	2014-03-01T02:46:31Z
dc.date.available	2014-03-01T02:46:31Z
dc.date.issued	2009	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/32691
dc.subject	AM-FM	en
dc.subject	Filterbank overlap	en
dc.subject	Instantaneous bandwidth	en
dc.subject	Instantaneous frequency	en
dc.subject	Speech recognition	en
dc.subject.other	Automatic speech recognition	en
dc.subject.other	Cepstral domain	en
dc.subject.other	Frequency domains	en
dc.subject.other	Instantaneous bandwidth	en
dc.subject.other	Instantaneous frequency	en
dc.subject.other	Relative error rates	en
dc.subject.other	Speaker recognition	en
dc.subject.other	Spectral moments	en
dc.subject.other	Stand -alone	en
dc.subject.other	Sub-bands	en
dc.subject.other	Time averages	en
dc.subject.other	Amplitude modulation	en
dc.subject.other	Bandwidth	en
dc.subject.other	Electric frequency measurement	en
dc.subject.other	Speech recognition	en
dc.title	Short-time instantaneous frequency and bandwidth features for speech recognition	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1109/ASRU.2009.5373305	en
heal.identifier.secondary	http://dx.doi.org/10.1109/ASRU.2009.5373305	en
heal.identifier.secondary	5373305	en
heal.publicationDate	2009	en
heal.abstract	In this paper, we investigate the performance of modulation related features and normalized spectral moments for automatic speech recognition. We focus on the short-time averages of the amplitude weighted instantaneous frequencies and bandwidths, computed at each subband of a mel-spaced filterbank. Similar features have been proposed in previous studies, and have been successfully combined with MFCCs for speech and speaker recognition. Our goal is to investigate the stand-alone performance of these features. First, it is experimentally shown that the proposed features are only moderately correlated in the frequency domain, and, unlike MFCCs, they do not require a transformation to the cepstral domain. Next, the filterbank parameters (number of filters and filter overlap) are investigated for the proposed features and compared with those of MFCCs. Results show that frequency related features perform at least as well as MFCCs for clean conditions, and yield superior results for noisy conditions; up to 50% relative error rate reduction for the AURORA3 Spanish task. © 2009 IEEE.	en
heal.journalName	Proceedings of the 2009 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2009	en
dc.identifier.doi	10.1109/ASRU.2009.5373305	en
dc.identifier.spage	103	en
dc.identifier.epage	106	en