Díaz de María, FernandoPeña Vicente, J.Gallardo Antolín, AscensiónPeláez Moreno, Carmen2008-03-142008-03-1420032003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings (ICASSP'03), vol. 2, pp. II-141-1440-7803-7663-31520-6149https://hdl.handle.net/10016/2316The 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.application/pdfeng© IEEEeAcoustic noiseDistortionEqualisersFiltering theoryParameter estimationRandom noiseSpectral analysisSpeech recognitionDistortion estimationFilter designInverse linear filterLinear distortionLinear equalizationLinear perturbationModulation spectraNoisy speech recognitionconference proceedingsTelecomunicaciones10.1109/ICASSP.2003.1202314open access