Comparison between DyWT- and EGG-based estimation of glottal closure instant for speech signal
Jongwon Seok, Youngho Son, Keunsung Bae · The Journal of the Acoustical Society of America · 1998
Recently, wavelet transform has found many applications. Mallat has shown that, with a proper choice of wavelet function, the local maxima of wavelet transformed signal indicate the position of the signal sharp variation points. Since the glottal closure causes sharp changes in the derivative of air flow in the glottis and transient in the speech signal, wavelet analysis can be used for detection of glottal closure instant (GCI) from the speech signal. It is known that the point of maximum negative value in a differentiated EGG signal agrees well with the closing time of the vocal folds. Due to the limited practical utility of the EGG signal, however, a speech-only-based GCI detection method is still needed. In this paper, GCI detection algorithm based on the dyadic wavelet transform (DyWT) is proposed and experimental results are shown. Using the EGG signal as a reference, experimental results are analyzed and discussed for evaluation of its performance. Preliminary experimental results show that DyWT-based GCI detection method has some speaker dependency and wavelet transformed speech signal at scale 4 gives more reliable GCI information than that of others. [This work has been partially supported by a grant from Korea Science and Engineering Foundation (KOSEF 971-0917- 103-2).]