ISCA Archive SMM 2022
ISCA Archive SMM 2022

Automatic detection of short-term sleepiness state. Sequence-to-Sequence modelling with global attention mechanism.

Edward L. Campbell, Laura Docío-Fernandez, Carmen García-Mateo, Andre Wittenborn, Jarek Krajewski, Nicholas Cummins

The Continuous Sleepiness detection task was a Sub-Challenge developed in the 2019 INTERSPEECH Computational Paralinguistics Challenge (ComParE). The associated speech corpus has been a reference in last years for the speech-based detection of sleepiness conditions. In this paper, we proposed a Sequenceto-Sequence model with global attention mechanism to accomplish this detection task. To the best of the authors’ knowledge, this is the first such an approach has been proposed for this task. Given the smaller size of this corpus, we utilise a small batch size, and augment our system with a score ensembling strategy to deliver the final decision. Despite the high complexity of our approach, it produces exceptionally competitive performances on the test-set, producing the second best performance to date. This result highlights the benefits of using deep-learning approaches, even with smaller sized speech-corpora.


doi: 10.21437/SMM.2022-2

Cite as: Campbell, E.L., Docío-Fernandez, L., García-Mateo, C., Wittenborn, A., Krajewski, J., Cummins, N. (2022) Automatic detection of short-term sleepiness state. Sequence-to-Sequence modelling with global attention mechanism.. Proc. Workshop on Speech, Music and Mind, 6-10, doi: 10.21437/SMM.2022-2

@inproceedings{campbell22_smm,
  author={Edward L. Campbell and Laura Docío-Fernandez and Carmen García-Mateo and Andre Wittenborn and Jarek Krajewski and Nicholas Cummins},
  title={{Automatic detection of short-term sleepiness state. Sequence-to-Sequence modelling with global attention mechanism.}},
  year=2022,
  booktitle={Proc. Workshop on Speech, Music and Mind},
  pages={6--10},
  doi={10.21437/SMM.2022-2}
}