ISCA Archive Interspeech 2013
ISCA Archive Interspeech 2013

Using generalized additive models and random forests to model prosodic prominence in German

Denis Arnold, Petra Wagner, R. Harald Baayen

The perception of prosodic prominence is influenced by different sources like different acoustic cues, linguistic expectations and context. We use a generalized additive model and a random forest to model the perceived prominence on a corpus of spoken German. Both models are able to explain over 80% of the variance. While the random forests give us some insights on the relative importance of the cues, the general additive model gives us insights on the interaction between different cues to prominence.


doi: 10.21437/Interspeech.2013-82

Cite as: Arnold, D., Wagner, P., Baayen, R.H. (2013) Using generalized additive models and random forests to model prosodic prominence in German. Proc. Interspeech 2013, 272-276, doi: 10.21437/Interspeech.2013-82

@inproceedings{arnold13_interspeech,
  author={Denis Arnold and Petra Wagner and R. Harald Baayen},
  title={{Using generalized additive models and random forests to model prosodic prominence in German}},
  year=2013,
  booktitle={Proc. Interspeech 2013},
  pages={272--276},
  doi={10.21437/Interspeech.2013-82}
}