Title :
A Walsh transform based endpoint detection of isolated utterances
Author :
Huang, John ; Tseng, Ben-dau
Author_Institution :
Dept. of Electr. Eng., California State Univ., Chico, CA, USA
Abstract :
The Walsh transform was applied to sequentially collected speech data in 128-point segments. From the Walsh spectra, the energy distribution can be generated and analyzed. The distribution along with an empirical threshold setting were used to detect the endpoints. To demonstrate the efficiency of the proposed method, experimental results along with comparisons to the commonly used endpoint detection algorithm of L.R. Rabiner and M.R. Sambur (1945) are included
Keywords :
speech analysis and processing; transforms; Walsh spectra; Walsh transform; empirical threshold setting; endpoint detection; energy distribution; isolated utterances; sequentially collected speech data; Algorithm design and analysis; Data analysis; Detection algorithms; Fourier series; Frequency; Signal processing; Speech analysis; Speech processing; Tellurium; Time domain analysis;
Conference_Titel :
Signals, Systems and Computers, 1991. 1991 Conference Record of the Twenty-Fifth Asilomar Conference on
Conference_Location :
Pacific Grove, CA
Print_ISBN :
0-8186-2470-1
DOI :
10.1109/ACSSC.1991.186468
