Fundamental Frequency Feature Extraction of speech based on the normalized Cross Correlation Function
cAo Meng-xia
ZHeNg Yong-guo
ZHeNg shang-xin
Abstract：The fundamental frequency (also called Pitch or F0) and its change rule are important features of speech signals for speech emotion recognition and voice print recognition and so on. But fundamental frequency extraction has always been the difficulty in the speech signal processing field, and the reason F0 not widely used in various applied in speech recognition is that so accurate and efifcient to extract the pitch can have important signiifcance in the speech signal processing. Based on the normalized cross correlation function, combining the cepstrum method, a new fundamental frequency extraction algorithm is proposed, and the experiment proved that the method in the fundamental frequency extraction has achieved good results.
Keywords：PitchF0Fundamental frequencyNccFspeechsignal processing
Publication Date：2014-01-01
Online Publishing Date：2026-05-22(First online date of this platform, not the publication date of the document)
Pages：3( 49-51 )