DocumentCode
1745705
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
fYear
2001
fDate
2001
Firstpage
193
Lastpage
196
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;
fLanguage
English
Publisher
ieee
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
Type
conf
DOI
10.1109/ISIMP.2001.925365
Filename
925365
Link To Document