ISCA Archive Interspeech 2010
ISCA Archive Interspeech 2010

A rule-based backchannel prediction model using pitch and pause information

Khiet P. Truong, Ronald Poppe, Dirk Heylen

We manually designed rules for a backchannel (BC) prediction model based on pitch and pause information. In short, the model predicts a BC when there is a pause of a certain length that is preceded by a falling or rising pitch. This model was validated against the Dutch IFADV Corpus in a corpus-based evaluation method. The results showed that our model performs slightly better than another well-known rule-based BC prediction model that uses only pitch information. We observed that the length of a pause preceding a BC is one of the important features in this model, next to the duration of the pitch slope at the end of an utterance. Further, we discuss implications of a corpus-based approach to BC prediction evaluation.


doi: 10.21437/Interspeech.2010-59

Cite as: Truong, K.P., Poppe, R., Heylen, D. (2010) A rule-based backchannel prediction model using pitch and pause information. Proc. Interspeech 2010, 3058-3061, doi: 10.21437/Interspeech.2010-59

@inproceedings{truong10_interspeech,
  author={Khiet P. Truong and Ronald Poppe and Dirk Heylen},
  title={{A rule-based backchannel prediction model using pitch and pause information}},
  year=2010,
  booktitle={Proc. Interspeech 2010},
  pages={3058--3061},
  doi={10.21437/Interspeech.2010-59},
  issn={2958-1796}
}