Affective and behavioural computing: Lessons learnt from the First Computational Paralinguistics Challenge.

•Review of the first Interspeech Challenge that actually ran under the label of Interspeech ComParE – the broadest to date – and the larger field.•Original fusion results of the best winning systems to establish a new baseline.•Additional novel analyses such as average confusion matrices of the participant’s systems.•Novel single feature baselines.•In-depth discussion of the performance variation and algorithms used.