The INTERSPEECH 2021 Computational Paralinguistics Challenge: COVID-19 Cough, COVID-19 Speech, Escalation & Primates
This work addresses the need for standardized benchmarks in computational paralinguistics, particularly for COVID-19 detection and other audio-based tasks, but it is incremental as it builds on existing competition frameworks and methods.
The paper introduced the INTERSPEECH 2021 Computational Paralinguistics Challenge, which tackled four classification problems including COVID-19 detection from cough and speech, escalation assessment in dialogues, and primate species classification, using baseline methods like COMPARE features and deep learning tools.
The INTERSPEECH 2021 Computational Paralinguistics Challenge addresses four different problems for the first time in a research competition under well-defined conditions: In the COVID-19 Cough and COVID-19 Speech Sub-Challenges, a binary classification on COVID-19 infection has to be made based on coughing sounds and speech; in the Escalation SubChallenge, a three-way assessment of the level of escalation in a dialogue is featured; and in the Primates Sub-Challenge, four species vs background need to be classified. 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 Deep Spectrum toolkit; in addition, we add deep end-to-end sequential modelling, and partially linguistic analysis.