ISCA Archive Interspeech 2007
ISCA Archive Interspeech 2007

Automatic pitch accent prediction for text-to-speech synthesis

Ian Read, Stephen Cox

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%.


doi: 10.21437/Interspeech.2007-224

Cite as: Read, I., Cox, S. (2007) Automatic pitch accent prediction for text-to-speech synthesis. Proc. Interspeech 2007, 482-485, doi: 10.21437/Interspeech.2007-224

@inproceedings{read07_interspeech,
  author={Ian Read and Stephen Cox},
  title={{Automatic pitch accent prediction for text-to-speech synthesis}},
  year=2007,
  booktitle={Proc. Interspeech 2007},
  pages={482--485},
  doi={10.21437/Interspeech.2007-224}
}