Title :
Noise robust pitch extraction based on auto-correlation analysis in the frequency domain
Author :
Tabata, Yuki ; Shimamura, Tetsuya
Author_Institution :
Dept. of Inf. & Comput. Sci., Saitama Univ., Urawa, Japan
Abstract :
This paper proposes an improved auto-correlation method for extracting fundamental frequency (pitch) from noisy speech. By transforming the auto-correlation function in the time domain to a synthetic wave consisting of the sum of cosine functions in the frequency domain, we improve the performance of pitch extraction from female speech. For male speech, the performance of the proposed method is competitive with that of the conventional method
Keywords :
correlation theory; frequency-domain analysis; noise; speech recognition; auto-correlation analysis; cosine functions; female speech; frequency domain; fundamental frequency extraction; male speech; noise robust pitch extraction; speech recognition; synthetic wave; Autocorrelation; Data mining; Delay effects; Flowcharts; Frequency domain analysis; Noise robustness; Signal processing; Speech analysis; Speech processing; Speech synthesis;
Conference_Titel :
Intelligent Multimedia, Video and Speech Processing, 2001. Proceedings of 2001 International Symposium on
Conference_Location :
Hong Kong
Print_ISBN :
962-85766-2-3
DOI :
10.1109/ISIMP.2001.925365
