Automatic Prosodic Phrase Annotation in a Corpus for Speech Synthesis

In order to improve speech naturalness of a unit selection TTS system it is necessary to annotate prosodic phrase boundaries in the whole source corpus, which is extremely difficult to achieve manually. It is thus usefull to employ a machine classifier. This paper discusses suitable feature selection for such classification of a Czech TTS corpus, presents results of experiments with linear and quadratic classifiers and artificial neural networks, and compares them with human annotators.