DETECTION OF OCCLUSIVES USING A WAVELET T RANSFORM

This paper describes the detection of stop consonants in the French la nguage with the help of the wavelet transform. Our hypothesis is that the burst of stop consonants can be approximated with a pulse. The det ection system is based on the study of the correlation functions betwe en the modulus of the impulse wavelet transform and the same transform of the speech signal. As we are using a Gaussian wavelet, the correla tion functions have a minimum before each maximum, where that maximum is synchronous with the burst of the stop consonant. Two signals S(M) and S(m) are computed. The are respectively the synchronous and asynch ronous sums of all the correlation functions. To localize the local mi nima of the S(m) function, two criteria are used. The temporal localis ation of the pulse is accomplished with certain local maxima of the si gnal S(M). The method of detection is tested with a corpus which has 1 37 unvoiced and 55 voiced stop consonants. The rate of detection is 94 % for the unvoiced stops and 75% for the voiced stops. This study show s that for detection, the burst of stop consonants can be modelled wit h a pulse.