International Journal of Swarm Intelligence and Evolutionary Computation

Using machine learning to detect COVID-19 in vocal audio

International Conference and Expo on Artificial Intelligence and Deep Learning

May 18, 2022 | Webinar

Madhurananda Pahar

Department of Electrical and Electronic Engineering, Stellenbosch University

Scientific Tracks Abstracts: Int J Swarm Evol Comput

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 generalization. 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.

Biography :

He is a motivated, hardworking, enthusiastic, experienced ML and AI engineer & researcher, working in signal processing for audio and smart sensors in bio-medicine and he seeks to expand his work experience in relative fields. Currently, he is involved in the application of deep learning to the detection and classification of TB and COVID-19 coughs in realworld environments as well as monitoring of patient behavior using smart sensors such as an accelerometer.