Title :
A new statistical approach for the automatic segmentation of continuous speech signals
Author :
Andre-Obrecht, Regine
Author_Institution :
IRISA, Rennes, France
fDate :
1/1/1988 12:00:00 AM
Abstract :
A statistical approach for the segmentation of a continuous speech signal to detect acoustic events is presented. Experiments are carried out to test the segmentation algorithms. Reasonable results are obtained with speech signals, although these are not exactly piecewise stationary. A comparison between the experimental results of automatic and handmade segmentations, demonstrates the potential acoustic-phonetic classification capability of the proposed algorithms
Keywords :
speech analysis and processing; statistical analysis; acoustic-phonetic classification; automatic segmentation; continuous speech signals; handmade segmentations; segmentation algorithms; statistical analysis; Acoustic signal detection; Acoustic testing; Event detection; Process control; Sequential analysis; Signal analysis; Signal processing; Speech analysis; Speech recognition; Statistical analysis;
Journal_Title :
Acoustics, Speech and Signal Processing, IEEE Transactions on