Filtered dynamics and fractal dimensions for noisy speech recognition

Pitsikalis, V; Maragos, P

dc.contributor.author	Pitsikalis, V	en
dc.contributor.author	Maragos, P	en
dc.date.accessioned	2014-03-01T01:24:24Z
dc.date.available	2014-03-01T01:24:24Z
dc.date.issued	2006	en
dc.identifier.issn	1070-9908	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/17250
dc.subject	Automatic speech recognition (ASR)	en
dc.subject	Filtered embedding	en
dc.subject	Fractal dimension	en
dc.subject	Phoneme classification	en
dc.subject.classification	Engineering, Electrical & Electronic	en
dc.subject.other	Acoustic noise	en
dc.subject.other	Acoustic signal processing	en
dc.subject.other	Fractals	en
dc.subject.other	Signal filtering and prediction	en
dc.subject.other	Signal to noise ratio	en
dc.subject.other	Speech processing	en
dc.subject.other	Automatic speech recognition (ASR)	en
dc.subject.other	Filtered embedding	en
dc.subject.other	Fractal dimensions	en
dc.subject.other	Mel-frequency cepstral coefficients	en
dc.subject.other	Speech recognition	en
dc.title	Filtered dynamics and fractal dimensions for noisy speech recognition	en
heal.type	journalArticle	en
heal.identifier.primary	10.1109/LSP.2006.879424	en
heal.identifier.secondary	http://dx.doi.org/10.1109/LSP.2006.879424	en
heal.language	English	en
heal.publicationDate	2006	en
heal.abstract	We explore methods from fractals and dynamical systems theory for robust processing and recognition of noisy speech. A speech signal is embedded in a multidimensional phase-space and is subsequently filtered exploiting aspects of its unfolded dynamics. Invariant measures (fractal dimensions) of the filtered signal are used as features in automatic speech recognition (ASR). We evaluate the new proposed features as well as the previously proposed multiscale fractal dimension via ASR experiments on the Aurora 2 database. The conducted experiments demonstrate relative improved word accuracy for the fractal features, especially at lower signal-to-noise ratio, when they are combined with the mel-frequency cepstral coefficients. © 2006 IEEE.	en
heal.publisher	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC	en
heal.journalName	IEEE Signal Processing Letters	en
dc.identifier.doi	10.1109/LSP.2006.879424	en
dc.identifier.isi	ISI:000242118400016	en
dc.identifier.volume	13	en
dc.identifier.issue	11	en
dc.identifier.spage	711	en
dc.identifier.epage	714	en