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

Thumbnail Image
Identifiers
URI: https://hdl.handle.net/10016/2316
ISSN: 1520-6149
ISBN: 0-7803-7663-3
DOI: 10.1109/ICASSP.2003.1202314
Files
diaz03.pdf (250.7 KB)
Publication date
2003
Defense date
Authors
Advisors
Tutors
Journal Title
Journal ISSN
Volume Title
Publisher
IEEE
Impact
Google Scholar
Export
Research Projects
Organizational Units
Journal Issue
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.
Description
Keywords
Acoustic noise, Distortion, Equalisers, Filtering theory, Parameter estimation, Random noise, Spectral analysis, Speech recognition, Distortion estimation, Filter design, Inverse linear filter, Linear distortion, Linear equalization, Linear perturbation, Modulation spectra, Noisy speech recognition
Bibliographic citation
2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings (ICASSP'03), vol. 2, pp. II-141-144
Collections
DTSC - GPM - Comunicaciones en congresos y otros eventos