This paper reports our initial experiments with automatic punctuation annotation from speech. We have focused on Czech broadcast news speech. The task can be defined as a classification of each inter-word boundary into one of target classes. We considered comma, sentence boundary and no punctuation as the target classes. We employed two statistical models prosodic model and language model. The prosodic model expresses relationships between prosodic quantities (such as pitch, speaking rate or loudness) and punctuation marks. We tested two implementations of this model decision tree and multi-layer perceptron. Hidden-event N-gram models were employed for language modeling. Instead of using an ordinary word-based model, we replaced infrequent word forms by their morphological tags and trained a mixed model. Scores from both models can be combined. The model combining language model with the decision tree yielded superior results. Testing on true words we achieved classification accuracy 95.2% and F-measure 78.2%.
Cite as: Kolar, J., Svec, J., Psutka, J. (2004) Automatic punctuation annotation in Czech broadcast news speech. Proc. 9th Conference on Speech and Computer (SPECOM 2004), 319-325
@inproceedings{kolar04_specom,
author={Jachym Kolar and Jan Svec and Josef Psutka},
title={{Automatic punctuation annotation in Czech broadcast news speech}},
year=2004,
booktitle={Proc. 9th Conference on Speech and Computer (SPECOM 2004)},
pages={319--325}
}