Your browser doesn't support javascript.
COVID-19 detection in cough, breath and speech using deep transfer learning and bottleneck features.
Pahar, Madhurananda; Klopper, Marisa; Warren, Robin; Niesler, Thomas.
  • Pahar M; Department of Electrical and Electronic Engineering, Stellenbosch University, South Africa. Electronic address: mpahar@sun.ac.za.
  • Klopper M; SAMRC Centre for Tuberculosis Research, DSI-NRF Centre of Excellence for Biomedical Tuberculosis Research, Division of Molecular Biology and Human Genetics, Faculty of Medicine and Health Sciences, Stellenbosch University, South Africa. Electronic address: marisat@sun.ac.za.
  • Warren R; SAMRC Centre for Tuberculosis Research, DSI-NRF Centre of Excellence for Biomedical Tuberculosis Research, Division of Molecular Biology and Human Genetics, Faculty of Medicine and Health Sciences, Stellenbosch University, South Africa. Electronic address: rw1@sun.ac.za.
  • Niesler T; Department of Electrical and Electronic Engineering, Stellenbosch University, South Africa. Electronic address: trn@sun.ac.za.
Comput Biol Med ; 141: 105153, 2022 02.
Article in English | MEDLINE | ID: covidwho-1588034
ABSTRACT
We present an experimental investigation into the effectiveness of transfer learning and bottleneck feature extraction in detecting COVID-19 from audio recordings of cough, breath and speech. This type of screening is non-contact, does not require specialist medical expertise or laboratory facilities and can be deployed on inexpensive consumer hardware such as a smartphone. We use datasets that contain cough, sneeze, speech and other noises, but do not contain COVID-19 labels, to pre-train three deep neural networks a CNN, an LSTM and a Resnet50. These pre-trained networks are subsequently either fine-tuned using smaller datasets of coughing with COVID-19 labels in the process of transfer learning, or are used as bottleneck feature extractors. Results show that a Resnet50 classifier trained by this transfer learning process delivers optimal or near-optimal performance across all datasets achieving areas under the receiver operating characteristic (ROC AUC) of 0.98, 0.94 and 0.92 respectively for all three sound classes coughs, breaths and speech. This indicates that coughs carry the strongest COVID-19 signature, followed by breath and speech. Our results also show that applying transfer learning and extracting bottleneck features using the larger datasets without COVID-19 labels led not only to improved performance, but also to a marked reduction in the standard deviation of the classifier AUCs measured over the outer folds during nested cross-validation, indicating better generalisation. We conclude that deep transfer learning and bottleneck feature extraction can improve COVID-19 cough, breath and speech audio classification, yielding automatic COVID-19 detection with a better and more consistent overall performance.
Subject(s)
Keywords

Full text: Available Collection: International databases Database: MEDLINE Main subject: COVID-19 Type of study: Diagnostic study / Prognostic study / Randomized controlled trials Limits: Humans Language: English Journal: Comput Biol Med Year: 2022 Document Type: Article

Similar

MEDLINE

...
LILACS

LIS


Full text: Available Collection: International databases Database: MEDLINE Main subject: COVID-19 Type of study: Diagnostic study / Prognostic study / Randomized controlled trials Limits: Humans Language: English Journal: Comput Biol Med Year: 2022 Document Type: Article