Title :
Low complexity noise power estimator for speech enhancement implemented on a dsPIC
Author :
Uriz, Alejandro Jose ; Castineira, Jorge ; Aguero, Pablo ; Tulli, Juan ; Hidalgo, Roberto ; Gonzalez, E.
Author_Institution :
Commun. Lab., Nat. Univ. of Mar del Plata, Mar del Plata, Argentina
Abstract :
In speech processing, the Signal-to-Noise Ratio (SNR) of the signal is an important feature. There are methods to reduce the noise contained into the speech which allow to obtain better results of the processing carried out. In this work a set of adaptive filtering methods are studied, with a deep analysis of the noise power estimators used to carry out the speech enhancement. Two baseline estimators are studied and a third estimator, which has lower computational complexity than the others, is presented. Finally, a set of implementations are performed in both MATLAB and a low cost hearing aid device based on the dsPIC33EP256MU806 from Microchip. A set of objective experiments and experimental measures are developed to verify the performance of the system.
Keywords :
adaptive filters; computational complexity; digital signal processing chips; discrete wavelet transforms; filtering theory; hearing aids; speech enhancement; DWT; MATLAB; SNR; adaptive filtering methods; baseline estimators; computational complexity; discrete wavelet transform; dsPIC33EP256MU806; low complexity noise power estimator; low cost digital signal processors; low cost hearing aid device; microchip; signal-to-noise ratio; speech enhancement; speech processing; Discrete wavelet transforms; Estimation; Kalman filters; Signal to noise ratio; Speech; Speech enhancement;
Conference_Titel :
Embedded Systems (SASE/CASE), 2014 Fifth Argentine Symposium and Conference on
Conference_Location :
Buenos Aires
Print_ISBN :
978-987-45523-0-3
DOI :
10.1109/SASE-CASE.2014.6914465
