INTERSPEECH 2007
8th Annual Conference of the International Speech Communication Association

Antwerp, Belgium
August 27-31, 2007

Automatic Pitch Accent Prediction for Text-to-Speech Synthesis

Ian Read, Stephen Cox

University of East Anglia, UK

Determining pitch accents in a sentence is a key task for a text-to-speech (TTS) system. We describe some methods for pitch accent assignment which make use of features that contain information about a complete phrase or sentence, in contrast to most previous work which has focused on using features local to a syllable or word. Pitch accent prediction is performed using three different techniques: N-gram models of syllable sequences, dynamic programming to match sequences of features, and decision trees. Using a C4.5 decision tree trained on a wide range of features, most notably each word's orthographic form and information extracted from the syntactic parse of the sentence, our feature set achieved a balanced error rate of 46.6%. This compares with the feature set used in [11] which had a balanced error rate of 55.55%.

Full Paper

Bibliographic reference.  Read, Ian / Cox, Stephen (2007): "Automatic pitch accent prediction for text-to-speech synthesis", In INTERSPEECH-2007, 482-485.