Weighted Autocor relation Function for Pitch Extraction from Noisy Speech

Abstract

In this paper, we discuss the use of a fuzzy weighting scheme to improve the accuracy of pitch extraction from noisy speech. The proposed fuzzy weighting scheme emphasizes the peak structure of the autocorrelation function (ACF) calculated from a speech frame while attenuating the components of ACF with smaller values. Experimental results show that by properly adjusting the fuzzy factor, the ACF-based fuzzy weighting scheme can provide higher capability in extracting the pitch information than some cepstrum-based and autocorrelation-based approaches in a noisy environment.