Linear equalization of the modulation spectra: a novel approach for noisy speech recognition

e-Archivo Repository

Show simple item record Díaz-de-María, Fernando Peña Vicente, J. Gallardo-Antolín, Ascensión Peláez-Moreno, Carmen 2008-03-14T12:01:31Z 2008-03-14T12:01:31Z 2003
dc.identifier.bibliographicCitation 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings (ICASSP'03), vol. 2, pp. II-141-144
dc.identifier.isbn 0-7803-7663-3
dc.identifier.issn 1520-6149
dc.description.abstract The paper tackles the problem of noisy speech recognition. In particular, we present a novel approach to the design of filters for processing the modulation spectrum, that we call linear equalization. We postulate that, as long as the distortion of the spectral parameters due to noise can be modeled as linear, an advantageous solution consists of estimating this linear perturbation system and designing its inverse system (the equalizer). Our experimental results show that the proposed method is very effective for three of the five types of noise considered.
dc.format.mimetype application/pdf
dc.language.iso eng
dc.publisher IEEE
dc.rights © IEEEe
dc.subject.other Acoustic noise
dc.subject.other Distortion
dc.subject.other Equalisers
dc.subject.other Filtering theory
dc.subject.other Parameter estimation
dc.subject.other Random noise
dc.subject.other Spectral analysis
dc.subject.other Speech recognition
dc.subject.other Distortion estimation
dc.subject.other Filter design
dc.subject.other Inverse linear filter
dc.subject.other Linear distortion
dc.subject.other Linear equalization
dc.subject.other Linear perturbation
dc.subject.other Modulation spectra
dc.subject.other Noisy speech recognition
dc.title Linear equalization of the modulation spectra: a novel approach for noisy speech recognition
dc.type article
dc.type conferenceObject
dc.description.status Publicado
dc.subject.eciencia Telecomunicaciones
dc.identifier.doi 10.1109/ICASSP.2003.1202314
dc.rights.accessRights openAccess
 Find Full text

Files in this item

*Click on file's image for preview. (Embargoed files's preview is not supported)

This item appears in the following Collection(s)

Show simple item record