Denoising Cough Sound Recordings Using Neural Networks

Authors

• Laya Jose, Australian Institute of Health Innovation, Macquarie University, Sydney, NSW 2109, AustraliaFollow
• Shlomo Berkovsky, Australian Institute of Health Innovation, Macquarie University, Sydney, NSW 2109, Australia
• Hao Xiong, Australian Institute of Health Innovation, Macquarie University, Sydney, NSW 2109, Australia
• Cecilia Mascolo, Department of Computer Science and Technology, University of Cambridge, Cambridge, United Kingdom
• Roneel V. Sharan, Australian Institute of Health Innovation, Macquarie University, Sydney, NSW 2109, Australia

Published

24-7-2023

Type of Work

Conference Presentation

Abstract

Objective cough sound evaluation is useful in the diagnosis and management of respiratory diseases. However, the performance of cough sound analysis models can degrade in the presence of background noises common in everyday environments. This brings forward the need for cough sound denoising. This work utilizes a method for denoising cough sound recordings using signal processing and machine learning techniques, inspired by research in the field of speech enhancement. It uses supervised learning to find a mapping between the noisy and clean spectra of cough sound signals using a fully connected feed-forward neural network. The method is validated on a dataset of 300 manually annotated cough sound recordings corrupted with babble noise. The effect of various signal processing and neural network parameters on denoising performance is investigated. The method is shown to improve cough sound quality and intelligibility and outperform conventional denoising methods.

References

1. S. Leconte et al., “Validated methods of cough assessment: a systematic review of the literature,” Respiration, vol. 81, no. 2, 2011.
2. J. I. Hall et al., “The present and future of cough counting tools,” J. Thorac. Dis., vol. 12, no. 9, pp. 5207–5223, 2020.
3. P. Porter et al., “A prospective multicentre study testing the diagnostic accuracy of an automated cough sound centred analytic system for the identification of common respiratory disorders in children,” Respir. Res., vol. 20, no. 1, Art. no. 81, 2019.
4. C. Brown et al., “Exploring automatic diagnosis of COVID-19 from crowdsourced respiratory sound data,” in Proc. 26th ACM SIGKDD Int. Conf. Knowl. Discovery Data Mining, 2020, pp. 3474–3484.
5. S. Omboni et al., “The worldwide impact of telemedicine during COVID-19: current evidence and recommendations for the future,” Conn. Health, vol. 1, no. 1, pp. 7–35, 2022.
6. R. V. Sharan et al., “Cough sound analysis for diagnosing croup in pediatric patients using biologically inspired features,” in Proc. 39th Annu. Int. Conf. IEEE Eng. Med. Biol. Soc., 2017, pp. 4578–4581.
7. Y. Wang et al., “Speech enhancement from fused features based on deep neural network and gated recurrent unit network,” EURASIP J. Adv. Signal Process., vol. 2021, no. 1, Art. no. 104, 2021.
8. D. Liu, P. Smaragdis, and M. Kim, “Experiments on deep learning for speech denoising,” in Proc. Annu. Conf. Int. Speech Commun. Assoc. (INTERSPEECH), 2014, pp. 2685–2689.
9. S. R. Park and J. W. Lee, “A fully convolutional neural network for speech enhancement,” in Proc. Annu. Conf. Int. Speech Commun. Assoc. (INTERSPEECH), 2017, pp. 1993–1997.
10. L. Orlandic, T. Teijeiro, and D. Atienza, “The COUGHVID crowdsourcing dataset, a corpus for the study of large-scale cough analysis algorithms,” Sci. Data, vol. 8, no. 1, Art. no. 156, 2021.
11. R. V. Sharan, H. Xiong, and S. Berkovsky, “Detecting cough recordings in crowdsourced data using CNN-RNN,” in Proc. IEEE EMBS Int. Conf. Biomed. Health Informat. (BHI), 2022, pp. 1–4.
12. E. Vincent, R. Gribonval, and C. Fevotte, “Performance measurement in blind audio source separation,” IEEE Trans. Audio Speech Lang. Process., vol. 14, no. 4, pp. 1462–1469, 2006.
13. C. H. Taal et al., “An algorithm for intelligibility prediction of time–frequency weighted noisy speech,” IEEE Trans. Audio Speech Lang. Process., vol. 19, no. 7, pp. 2125–2136, 2011.
14. A. W. Rix et al., “Perceptual evaluation of speech quality (PESQ)-a new method for speech quality assessment of telephone networks and codecs,” in Proc. IEEE Int. Conf. Acoust. Speech Signal Process., 2001, pp. 749–752.
15. C. Plapous, C. Marro, and P. Scalart, “Improved signal-to-noise ratio estimation for speech enhancement,” IEEE Trans. Audio Speech Lang. Process., vol. 14, no. 6, pp. 2098–2108, 2006.

Citation

Jose, L., Berkovsky, S., Xiong, H., Mascolo, H., & Sharan, R. V. (2023). Denoising cough sound recordings using neural networks. In 2023 45th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC) (pp. 1-4). IEEE. https://doi.org/10.1109/EMBC40787.2023.10340687

Link to Published Work

https://ieeexplore.ieee.org/abstract/document/10340687/citations#citations