Automatic recognition of prosodic phrases

The authors report on the development of two algorithms to automatically detect prosodic phrases. The first algorithm uses simple frame-based likelihood classifiers to detect breaths and silences, which yields a large percentage of major phrase breaks. To label other levels of prosodic structure, a second algorithm is introduced that uses phoneme durations given by a speech recognizer in conjunction with a tree quantizer and hidden Markov model to label a hierarchy of prosodic phrase breaks. This second algorithm yields phrase break predictions that have good correlation with hand labels, and correctly detects more than 90% of the major phrase boundaries