DocumentCode :
239777
Title :
Instantaneous pitch estimation based on empirical wavelet transform
Author :
Yusheng Li ; Biao Xue ; Hong Hong ; Xiaohua Zhu
Author_Institution :
Sch. of Electron. & Opt. Eng., Nanjing Univ. of Sci. & Technol., Nanjing, China
fYear :
2014
fDate :
20-23 Aug. 2014
Firstpage :
250
Lastpage :
253
Abstract :
In this paper, a novel approach is proposed specially for capturing the instantaneous pitch that may reveals some innate character of the speech. Firstly, the original signal is decomposed into several modes with empirical wavelet transform, and then the mode containing the pitch is picked out, finally the instantaneous pitch is calculated via Hilbert transform. Intensive evaluation and direct comparisons with existing method are conducted with the standard Chinese and English speech database, all showing the effectiveness of the proposed method in acquiring the instantaneous pitch.
Keywords :
Hilbert transforms; speech processing; wavelet transforms; Chinese speech database; English speech database; Hilbert transform; empirical wavelet transform; instantaneous pitch estimation; intensive evaluation; signal decomposition; speech character; Databases; Digital signal processing; Estimation; Speech; Speech processing; Wavelet transforms; empirical wavelet transform; hilbert transform; instantaneous pitch;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Digital Signal Processing (DSP), 2014 19th International Conference on
Conference_Location :
Hong Kong
Type :
conf
DOI :
10.1109/ICDSP.2014.6900838
Filename :
6900838
Link To Document :
بازگشت