An objective distance measure which is able to predict audible discontinuities in concatenative speech synthesis systems is very important. Previous results showed that linear approaches are not very effective to detect audible discontinuities. The best result was obtained by using the Kullback-Leibler distance on power spectra with the rate of 37%. In this paper, we present two nonlinear approaches for the detection of discontinuities. The first method is based on a nonlinear harmonic model for speech while the second method is based on the demodulation of speech in an amplitude and a frequency component using the Teager energy operator. Results show that detection rate can exceed 70%, which is an improvement of about 95% over previous published results.
展开▼
