Journal
COMPUTERS IN BIOLOGY AND MEDICINE
Volume 141, Issue -, Pages -Publisher
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.compbiomed.2021.105153
Keywords
COVID-19; Cough; Breath; Speech; Transfer learning; Bottleneck features
Categories
Funding
- South African Medical Research Council (SAMRC) through its Division of Research Capacity Development under the Research Capacity Development Initiative
- South African National Treasury
- European Union through the EDCTP2 programme [TMA2017CDF-1885]
- Telkom South Africa
- South African Centre for High Performance Computing (CHPC)
Ask authors/readers for more resources
The study demonstrates that using transfer learning and bottleneck feature extraction can enhance the accuracy and consistency of detecting COVID-19 from audio recordings of cough, breath, and speech. Coughs display the strongest COVID-19 signatures, followed by breath and speech.
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.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available