The INTERSPEECH 2020 Computational Paralinguistics ChallengE (ComParE)

Wed-SS-1-4-1 The INTERSPEECH 2020 Computational Paralinguistics Challenge: Elderly Emotion, Breathing & Masks

Björn Schuller(University of Augsburg / Imperial College London), Anton Batliner(University of Augsburg), Christian Bergler(Friedrich-Alexander-University Erlangen-Nuremberg, Department of Computer Science, Pattern Recognition Lab), Eva-Maria Messner(University of Ulm), Antonia Hamilton(UCL), Shahin Amiriparian(University of Augsburg / Technische Universität München), Alice Baird(University of Augsburg), Georgios Rizos(Imperial College London), Maximilian Schmitt(Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg), Lukas Stappen(University of Augsburg), Harald Baumeister(University of Ulm), Alexis Deighton MacIntyre(UCL) and Simone Hantke(audEERING)
Abstract: The INTERSPEECH 2020 Computational Paralinguistics Challenge addresses three different problems for the first time in a research competition under well-defined conditions: In the Elderly EmotionSub-Challenge, arousal and valence in the speech of elderly individuals have to be modelled as a 3-class problem; in theBreathingSub-Challenge, breathing has to be assessed as a regression problem; and in theMaskSub-Challenge, speech with-out and with a surgical mask has to be told apart. We describe the Sub-Challenges, baseline feature extraction, and classifiers based on the ‘usual’ ComParE and BoAW features as well as deep unsupervised representation learning using the auDeep toolkit, and deep feature extraction from pre-trained CNNs using the DeepSpectrum toolkit; in addition, we partially add deep end-to-end sequential modelling, and, for the first time in the challenge, linguistic analysis.
Student Information

Student Events

Travel Grants