Predicting intonational boundaries automatically from text
Michelle Q. Wang, Julia Hirschberg · 1991
Relating the intonational characteristics of an utterance to other features inferable from its text is important both for speech recognition and for speech synthesis. This work investigates techniques for predicting the location of intonational phrase boundaries in natural speech, through analyzing a utterances from the DARPA Air Travel Information Service database. For statistical modeling, we employ Classification and Regression Tree (CART) techniques. We achieve success rates of just over 90%.