Exploring Fusion Methods and Feature Space for the Classification of Paralinguistic Information

David Tavarez, Xabier Sarasola, Agustin Alonso, Jon Sanchez, Luis Serrano, Eva Navas, Inma Hernáez


This paper introduces the different systems developed by Aholab Signal Processing Laboratory for The INTERSPEECH 2017 Computational Paralinguistics Challenge, which includes three different subtasks: Addressee, Cold and Snoring classification. Several classification strategies and features related with the spectrum, prosody and phase have been tested separately and further combined by using different fusion techniques, such as early fusion by means of multi-feature vectors, late fusion of the standalone classifier scores and label fusion via weighted voting. The obtained results show that the applied fusion methods improve the performance of the standalone detectors and provide systems capable of outperforming the baseline systems in terms of UAR.


 DOI: 10.21437/Interspeech.2017-1378

Cite as: Tavarez, D., Sarasola, X., Alonso, A., Sanchez, J., Serrano, L., Navas, E., Hernáez, I. (2017) Exploring Fusion Methods and Feature Space for the Classification of Paralinguistic Information. Proc. Interspeech 2017, 3517-3521, DOI: 10.21437/Interspeech.2017-1378.


@inproceedings{Tavarez2017,
  author={David Tavarez and Xabier Sarasola and Agustin Alonso and Jon Sanchez and Luis Serrano and Eva Navas and Inma Hernáez},
  title={Exploring Fusion Methods and Feature Space for the Classification of Paralinguistic Information},
  year=2017,
  booktitle={Proc. Interspeech 2017},
  pages={3517--3521},
  doi={10.21437/Interspeech.2017-1378},
  url={http://dx.doi.org/10.21437/Interspeech.2017-1378}
}