ISCA Archive Interspeech 2021
ISCA Archive Interspeech 2021

Classification of COVID-19 from Cough Using Autoregressive Predictive Coding Pretraining and Spectral Data Augmentation

John Harvill, Yash R. Wani, Mark Hasegawa-Johnson, Narendra Ahuja, David Beiser, David Chestek

Serum and saliva-based testing methods have been crucial to slowing the COVID-19 pandemic, yet have been limited by slow throughput and cost. A system able to determine COVID-19 status from cough sounds alone would provide a low cost, rapid, and remote alternative to current testing methods. We explore the applicability of recent techniques such as pre-training and spectral augmentation in improving the performance of a neural cough classification system. We use Autoregressive Predictive Coding (APC) to pre-train a unidirectional LSTM on the COUGHVID dataset. We then generate our final model by fine-tuning added BLSTM layers on the DiCOVA challenge dataset. We perform various ablation studies to see how each component impacts performance and improves generalization with a small dataset. Our final system achieves an AUC of 85.35 and places third out of 29 entries in the DiCOVA challenge.


doi: 10.21437/Interspeech.2021-799

Cite as: Harvill, J., Wani, Y.R., Hasegawa-Johnson, M., Ahuja, N., Beiser, D., Chestek, D. (2021) Classification of COVID-19 from Cough Using Autoregressive Predictive Coding Pretraining and Spectral Data Augmentation. Proc. Interspeech 2021, 926-930, doi: 10.21437/Interspeech.2021-799

@inproceedings{harvill21_interspeech,
  author={John Harvill and Yash R. Wani and Mark Hasegawa-Johnson and Narendra Ahuja and David Beiser and David Chestek},
  title={{Classification of COVID-19 from Cough Using Autoregressive Predictive Coding Pretraining and Spectral Data Augmentation}},
  year=2021,
  booktitle={Proc. Interspeech 2021},
  pages={926--930},
  doi={10.21437/Interspeech.2021-799}
}