System and method for determining pitch contours

摘要: A system and method are provided for automatically computing local pitch contours from textual input to produce that closely mimic those found in natural speech. The methodology of the invention incorporates parameterized equations whose parameters can be estimated directly speech recordings. That a model based on premise instantiating particular contour class described as distortions temporal frequency domains single, underlying contour. After nature different classes has been established, predicted models synthetic utterance by adding individual intonational adjusting boundaries these match adjacent intonation curves.