ISCA Archive SpeechProsody 2002
ISCA Archive SpeechProsody 2002

Dialog act classification from prosodic features using support vector machines

Raul Fernandez, Rosalind W. Picard

In this work we investigate the use of support vector machines (SVMs) and discriminative learning techniques on the task of automatic classification of dialogue acts (DAs) from prosodic cues. We implement and test these classifiers on solving an 8- DA classification task on the Spanish CallHome database and report preliminary recognition rates of 47.3% with respect to a 20.4% chance-level rate, which represents an improvement over previously reported work using decision trees and neural network classifiers. Although prosodic cues alone may not suf- fice for robust classification of DAs, we report results that suggest that SVMs offer an interesting alternative to previously explored models, and should be further explored to improve the contribution of prosodic models to the classification task.


Cite as: Fernandez, R., Picard, R.W. (2002) Dialog act classification from prosodic features using support vector machines. Proc. Speech Prosody 2002, 291-294

@inproceedings{fernandez02_speechprosody,
  author={Raul Fernandez and Rosalind W. Picard},
  title={{Dialog act classification from prosodic features using support vector machines}},
  year=2002,
  booktitle={Proc. Speech Prosody 2002},
  pages={291--294}
}