Title :
Use of fuzzy weighted autocorrelation function for pitch extraction from noisy speech
Author_Institution :
Dept. of Electr. Eng., Ming Chi Inst. of Technol., Taipei, Taiwan
fDate :
9/12/2002 12:00:00 AM
Abstract :
An investigation is presented into the feasibility of incorporating a fuzzy weighting scheme into the calculation of an autocorrelation function for pitch extraction. Simulation results reveal that the proposed method provides better robustness against background noise than the conventional approaches for extracting pitch period in a noisy environment
Keywords :
AWGN; correlation methods; fuzzy systems; speech processing; autocorrelation function; average magnitude difference function; background noise; cepstrum method; fuzzy weighting scheme; noisy speech; pitch extraction; simulation results; speech analysis-synthesis system;
Journal_Title :
Electronics Letters
DOI :
10.1049/el:20020736