Mallol Ragolta, AdriàCuesta, HelenaGómez Gutiérrez, Emilia, 1975-Schuller, Björn2023-03-012023-03-012021Mallol-Ragolta A, Cuesta H, Gómez E, Schuller BW. Cough-based COVID-19 detection with contextual attention convolutional neural networks and gender information. In: Proc. Interspeech 2021; 2021 Aug 30-Sep 3; Brno, Czech Republic. [Baixas]: International Speech Communication Association; 2021. p. 941-5. DOI: 10.21437/Interspeech.2021-1052http://hdl.handle.net/10230/55988Comunicació presentada a INTERSPEECH 2021, celebrat del 30 d'agost al 3 de setembre de 2021 a Brno, Txèquia.The aim of this contribution is to automatically detect COVID19 patients by analysing the acoustic information embedded in coughs. COVID-19 affects the respiratory system, and, consequently, respiratory-related signals have the potential to contain salient information for the task at hand. We focus on analysing the spectrogram representations of cough samples with the aim to investigate whether COVID-19 alters the frequency content of these signals. Furthermore, this work also assesses the impact of gender in the automatic detection of COVID-19. To extract deep-learnt representations of the spectrograms, we compare the performance of a cough-specific, and a Resnet18 pre-trained Convolutional Neural Network (CNN). Additionally, our approach explores the use of contextual attention, so the model can learn to highlight the most relevant deep-learnt features extracted by the CNN. We conduct our experiments on the dataset released for the Cough Sound Track of the DICOVA 2021 Challenge. The best performance on the test set is obtained using the Resnet18 pre-trained CNN with contextual attention, which scored an Area Under the Curve (AUC) of 70.91 % at 80 % sensitivity.application/pdfeng© 2021 ISCAinfo:eu-repo/semantics/conferenceObjecthttp://dx.doi.org/10.21437/Interspeech.2021-1052COVID-19acousticsmachine learningrespiratory diagnosishealthcareinfo:eu-repo/semantics/openAccess