Automatic recognition of intonational features

The authors report the initial development of an algorithm to automatically detect boundary tones and prominences in continuous speech. Utilizing phoneme durations given by a speech recognizer, the authors use a tree quantizer and hidden Markov model to label these intonational features. In speaker-independent tests on a corpus of professionally read speech, 77% of the boundary tones were correctly detected while 3% of the detections were false alarms. For prominences, the corresponding numbers were 86% and 14%