Evaluating the COVID-19 Identification ResNet (CIdeR) on the INTERSPEECH COVID-19 From Audio Challenges

We report on cross-running the recent COVID-19 Identification ResNet (CIdeR) on the two Interspeech 2021 COVID-19 diagnosis from cough and speech audio challenges: ComParE and DiCOVA. CIdeR is an end-to-end deep learning neural network originally designed to classify whether an individual is COVID-positive or COVID-negative based on coughing and breathing audio recordings from a published crowdsourced dataset. In the current study, we demonstrate the potential of CIdeR at binary COVID-19 diagnosis from both the COVID-19 Cough and Speech Sub-Challenges of INTERSPEECH 2021, ComParE and DiCOVA. CIdeR achieves significant improvements over several baselines.

[1]  Srikanth Raj Chetupalli,et al.  Coswara - A Database of Breathing, Cough, and Voice Sounds for COVID-19 Diagnosis , 2020, INTERSPEECH.

[2]  George Trigeorgis,et al.  Adieu features? End-to-end speech emotion recognition using a deep convolutional recurrent network , 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[3]  Thomas F. Quatieri,et al.  A Framework for Biomarkers of COVID-19 Based on Coordination of Speech-Production Subsystems , 2020, IEEE Open Journal of Engineering in Medicine and Biology.

[4]  Prasanta Kumar Ghosh,et al.  DiCOVA Challenge: Dataset, task, and baseline system for COVID-19 diagnosis using acoustics , 2021, Interspeech.

[5]  Gadi Pinkas,et al.  SARS-CoV-2 Detection From Voice , 2020, IEEE Open Journal of Engineering in Medicine and Biology.

[6]  Cecilia Mascolo,et al.  Exploring Automatic Diagnosis of COVID-19 from Crowdsourced Respiratory Sound Data , 2020, KDD.

[7]  Panagiotis Tzirakis,et al.  End-2-End COVID-19 Detection from Breath & Cough Audio , 2021, ArXiv.

[8]  Björn W. Schuller,et al.  The voice of COVID-19: Acoustic correlates of infection in sustained vowelsa) , 2020, The Journal of the Acoustical Society of America.

[9]  Muhammad Nabeel,et al.  AI4COVID-19: AI enabled preliminary diagnosis for COVID-19 from cough samples via an app , 2020, Informatics in Medicine Unlocked.

[10]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[11]  K. A. Moyse.  Lateral flow tests need low false positives for antibodies and low false negatives for virus , 2021, British medical journal.

[12]  Deepu Vijayasenan,et al.  COVID-19 Patient Detection from Telephone Quality Speech Data , 2020, ArXiv.

[13]  Brian Subirana,et al.  COVID-19 Artificial Intelligence Diagnosis Using Only Cough Recordings , 2020, IEEE Open Journal of Engineering in Medicine and Biology.

[14]  Elisabeth Mahase,et al.  Covid-19: Innova lateral flow test is not fit for “test and release” strategy, say experts , 2020, BMJ.

[15]  Cecilia Mascolo,et al.  Exploring Automatic COVID-19 Diagnosis via Voice and Symptoms from Crowdsourced Data , 2021, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[16]  J. Hanley,et al.  The meaning and use of the area under a receiver operating characteristic (ROC) curve. , 1982, Radiology.

[17]  A. Charlett,et al.  Duration of infectiousness and correlation with RT-PCR cycle threshold values in cases of COVID-19, England, January to May 2020 , 2020, Euro surveillance : bulletin Europeen sur les maladies transmissibles = European communicable disease bulletin.

[18]  Bjorn W. Schuller,et al.  Detecting COVID-19 from Breathing and Coughing Sounds using Deep Neural Networks , 2020, 2021 IEEE 34th International Symposium on Computer-Based Medical Systems (CBMS).

[19]  Harry D. Nuttall,et al.  COVID-19: Rapid antigen detection for SARS-CoV-2 by lateral flow assay: A national systematic evaluation of sensitivity and specificity for mass-testing , 2021, EClinicalMedicine.

[20]  Björn Schuller,et al.  COVID-19 detection from audio: seven grains of salt , 2021, The Lancet Digital Health.

[21]  J. Peto,et al.  Weekly COVID-19 testing with household quarantine and contact tracing is feasible and would probably end the epidemic , 2020, Royal Society Open Science.

[22]  David Atienza,et al.  The COUGHVID crowdsourcing dataset, a corpus for the study of large-scale cough analysis algorithms , 2021, Scientific data.

[23]  Arsha Nagrani,et al.  Cough Against COVID: Evidence of COVID-19 Signature in Cough Sounds , 2020, ArXiv.

[24]  Cecilia Mascolo,et al.  The INTERSPEECH 2021 Computational Paralinguistics Challenge: COVID-19 Cough, COVID-19 Speech, Escalation & Primates , 2021, Interspeech.