``Prediction of Sleepiness Ratings from Voice by Man and Machine": a perceptual experiment replication study

Following the release of the SLEEP corpus during the Interspeech 2019 paralinguistic continuous sleepiness estimation challenge, a paper presented at Interspeech 2020 by Huckvale \textit{et al.} examined the reasons for the poor performance of the models proposed for this task. Careful analyses of the corpus led to the conclusion that its bias makes it hazardous to use for training machine learning systems, but a perceptual experiment on a subset of this corpus seemed to indicate that human hearing is however able to estimate sleepiness on this corpus. In this study, we present the results of the Endymion replication study, in which the same samples were rated by thirty French-speaking naive listeners. We then discuss the causes of the differences between the two studies and examine the effect of listener and sample characteristics on annotation performances.