Pahar, M. orcid.org/0000-0002-5926-0144, Klopper, M. orcid.org/0000-0002-9318-8289, Warren, R. orcid.org/0000-0001-5741-7358 et al. (1 more author) (2022) COVID-19 detection in cough, breath and speech using deep transfer learning and bottleneck features. Computers in Biology and Medicine, 141. 105153. ISSN 0010-4825
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.
Metadata
Item Type: | Article |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2021 Elsevier. This is an author produced version of a paper subsequently published in Computers in Biology and Medicine. Uploaded in accordance with the publisher's self-archiving policy. Article available under the terms of the CC-BY-NC-ND licence (https://creativecommons.org/licenses/by-nc-nd/4.0/). |
Keywords: | Bottleneck features; Breath; COVID-19; Cough; Speech; Transfer learning; COVID-19; Cough; Humans; Machine Learning; SARS-CoV-2; Speech |
Dates: |
|
Institution: | The University of Sheffield |
Academic Units: | The University of Sheffield > Faculty of Engineering (Sheffield) > Department of Computer Science (Sheffield) |
Depositing User: | Symplectic Sheffield |
Date Deposited: | 21 Jan 2025 09:44 |
Last Modified: | 24 Jan 2025 15:13 |
Status: | Published |
Publisher: | Elsevier BV |
Refereed: | Yes |
Identification Number: | 10.1016/j.compbiomed.2021.105153 |
Related URLs: | |
Sustainable Development Goals: | |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:221840 |