A multiresolution approach to closed glottis interval determination

We consider the closed glottis interval determination problem from the point of view of getting a multiresolution signal representation and searching for maxima in successive scales. Within this framework, an octave band decomposition, using half-band finite impulse response (FIR) filters is very promising, since those filters are less constrained than the orthogonal and biorthogonal wavelet filters. A number of experiments with synthesized signals argue the superior performance of the multiresolution approach in comparison with the traditional covariance approaches.