Exploring Automatic Diagnosis of COVID-19 from Crowdsourced Respiratory Sound Data
Open accessThe DOI matches its Crossref record; 35 of the 35 references it cites were found in a registry or an index.
Abstract
Audio signals generated by the human body (e.g., sighs, breathing, heart, digestion, vibration sounds) have routinely been used by clinicians as indicators to diagnose disease or assess disease progression. Until recently, such signals were usually collected through manual auscultation at scheduled visits. Research has now started to use digital technology to gather bodily sounds (e.g., from digital stethoscopes) for cardiovascular or respiratory examination, which could then be used for automatic analysis. Some initial work shows promise in detecting diagnostic signals of COVID-19 from voice and coughs. In this paper we describe our data analysis over a large-scale crowdsourced dataset of respiratory sounds collected to aid diagnosis of COVID-19. We use coughs and breathing to understand how discernible COVID-19 sounds are from those in asthma or healthy controls. Our results show that even a simple binary machine learning classifier is able to classify correctly healthy and COVID-19 sounds. We also show how we distinguish a user who tested positive for COVID-19 and has a cough from a healthy user with a cough, and users who tested positive for COVID-19 and have a cough from users with asthma and a cough. Our models achieve an AUC of above 80% across all tasks. These results are preliminary and only scratch the surface of the potential of this type of data and audio-based machine learning. This work opens the door to further investigation of how automatically analysed respiratory patterns could be used as pre-screening signals to aid COVID-19 diagnosis.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures








Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“COVID-19 has been studied using different audio sounds, including voice, breathing and cough sounds [10,29,79,80].”
From Human-centred artificial intelligence for mobile health sensing: challenges and opportunities (2023) · cites this paper as [79]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Davis, S., & Mermelstein, P. (1980) · IEEE Transactions on Acoustics, Speech, and Signal Processing · doi:10.1109/tassp.1980.1163420 · Cited by 5,465 · cited 1×
“ents obtained from the short-term power spectrum, based on a linear cosine transform of the log power spectrum on a nonlinear Mel scale. MFCCs are amongst the most common features in audio processing [9]. We use the first 13 components. • ∆-MFCC: the temporal differential (delta) of the MFCC [1]. ∆2-MFCC: the differen…”
Backgroundlibrosa: Audio and Music Signal Analysis in Python
McFee, B., Raffel, C., Liang, D., Ellis, D., McVicar, M., Battenberg, E., & Nieto, O. (2015) · Proceedings of the Python in Science Conference · doi:10.25080/majora-7b98e3ed-003 · Cited by 3,033 · cited 1×
“ustrates the data processing pipelines. 4.1 Feature extraction HandcraftedFeatures.The raw sound waveform recorded by the apps is resampled to 22kHz, a standard value for audio tasks. We used librosa [20] as our audio processing library. From the resampled audio various handcrafted features are extracted at the frame…”
MethodInfluentialCNN architectures for large-scale audio classification
Hershey, S., Chaudhuri, S., Ellis, D. P. W., Gemmeke, J. F., Jansen, A., Moore, R. C., Plakal, M., Platt, D., Saurous, R. A., Seybold, B., et al. (2017) · 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2017.7952132 · Cited by 2,023
(2010) · doi:10.5555/1756006.1859921 · Cited by 1,924
Real-time tracking of self-reported symptoms to predict potential COVID-19
Menni, C., Valdes, A. M., Freidin, M. B., Sudre, C. H., Nguyen, L. H., Drew, D. A., Ganesh, S., Varsavsky, T., Cardoso, M. J., El-Sayed Moustafa, J. S., et al. (2020) · Nature Medicine · doi:10.1038/s41591-020-0916-2 · Cited by 1,517
KERNEL METHODS IN MACHINE LEARNING
Hofmann, T., Schölkopf, B., & Smola, A. J. (2008) · Cited by 1,408
AI4COVID-19: AI enabled preliminary diagnosis for COVID-19 from cough samples via an app
Imran, A., Posokhova, I., Qureshi, H. N., Masood, U., Riaz, M. S., Ali, K., John, C. N., Hussain, M. I., & Nabeel, M. (2020) · Informatics in Medicine Unlocked · doi:10.1016/j.imu.2020.100378 · Cited by 621 · cited 2×
“In [17] a study of detection of coughs related to COVID-19 is presented using a cohort of 48 COVID-19 tested patients versus other pathology coughs on which an AI model is trained.”
MethodEmotionSense: a mobile phones based adaptive platform for experimental social psychology research
Rachuri, K. K., Musolesi, M., Mascolo, C., Rentfrow, P. J., Longworth, C., & Aucinas, A. (2010) · Proceedings of the 12th ACM international conference on Ubiquitous computing · doi:10.1145/1864349.1864393 · Cited by 508 · cited 1×
“In Emotionsense [26], the phone microphone is used as a sensor for users’ emotion detection in-thewild through Gaussian mixture models.”
MethodProceedings of the 13th International Society for Music Information Retrieval Conference, ISMIR 2012
Gouyon, F., Herrera, P., Martins, L. G., & Müller, M. A. (2012) · Cited by 446
Beat Tracking by Dynamic Programming
Ellis, D. P. W. (2007) · Journal of New Music Research · doi:10.1080/09298210701653344 · Cited by 391 · cited 1×
“• Tempo : the beats of the signals by measuring the onset strength, commonly used in music information retrieval [11].”
Cited by
Items 301–400 of 493
Impact of data-splits on generalization: Identifying COVID-19 from cough and contextPreprint
Sharma, M., Shenoy, N., Doshi, J., Bagad, P., Dalmia, A., Bhamare, P., Mahale, A., Rane, S., Agrawal, N., & Panicker, R. A. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.03851 · Cited by 4
“Unlike crowd-sourced datasets such as Brown et al. (2020), Orlandic et al.”
MethodInfluentialThe AI Mechanic: Acoustic Vehicle Characterization Neural NetworksPreprint
Terwilliger, A. M., & Siegel, J. E. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2205.09667 · Cited by 6
“Applications that utilize DL for sound-based tasks range from music genre clas-sification [33, 45] to medical diagnoses [15, 19, 12] to animal recognition [40, 64, 74, 82, 80, 11] and more [39, 67, 38].”
BackgroundIbam, E. O., & Oluwagbemi, J. B. (2026) · Journal of Computing Theories and Applications · doi:10.62411/jcta.14944 · Cited by 5
“Conventional diagnosis relies heavily on chest radiography and laboratory testing, which are resource-intensive, time-consuming, and unsuitable for remote or continuous monitoring scenarios [4], [5].”
Nguyen, H. T. T., Le, V. Q., Dinh‐Xuan, A. T., & Nguyen, L. N. (2026) · Diagnostics · doi:10.3390/diagnostics16081127 · Cited by 3
“Across studies, reported performance varies widely depending on dataset composition, recording conditions, and model architecture, highlighting the need for standardized data collection and independent validation across diverse populations [12,26,40–42].”
Anderson, W., & Simske, S. J. (2020) · IEEE International Conference on Healthcare Informatics (ICHI) · doi:10.1109/ichi48887.2020.9374337 · Cited by 3
“Brown et al. have begun studies into using recordings of both speech and coughing, along with an input of symptoms by the user, to diagnose COVID-19 with mild success to date [24].”
BackgroundCNN-based Diagnosis System on Skin Cancer using Ensemble Method Weighted by Cubic Precision
Jiang, P. (2021) · International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT) · doi:10.1109/ainit54228.2021.00038 · Cited by 3
Zaabi, M., Hariri, W., Smaoui, N., & Haouli, I.-E. (2022) · IEEE Information Technologies & Smart Industrial Systems (ITSIS) · doi:10.1109/itsis56166.2022.10118380 · Cited by 3
“The authors in [24] have described a data analysis that can help with COVID-19 diagnosis.”
BackgroundImpact of Health Information Technology Tools on Patient Safety in the Indian Healthcare Industry
Angayarkanni, S. A., Rajaram, V., Pandimurugan, V., & Nagarajan, M. (2023) · The Open Biomedical Engineering Journal · doi:10.2174/18741207-v17-e230925-2022-ht28-4371-9 · Cited by 4
Convolutional Neural Network for the Detection of Respiratory Crackles
Stas, T., Lauwers, E., Ides, K., Verhulst, S. L., Delputte, P., & Steckel, J. (2024) · IEEE Access · doi:10.1109/access.2024.3472839 · Cited by 3
“Some systems try to draw a diagnostic conclusion based on the patients respiratory recording [5], [6], [7], [8].”
BackgroundEnsemble deep learning models for respiratory disease detection using cough analysis
Bouzammour, B., Zaz, G., Marktani, M. A., Chougrad, H., Touhafi, A., & Jorio, M. (2025) · Journal of Engineering Research · doi:10.1016/j.jer.2025.08.017 · Cited by 3
Karatas, E., Adali, B., Aydın, Ö., & Dalkılıç, G. (2021) · Innovations in Intelligent Systems and Applications Conference (ASYU) · doi:10.1109/asyu52992.2021.9598961 · Cited by 3
“Providing users with medical advice can be controversial [5].”
BackgroundShen, J., Zhang, X., Wang, W., Huang, Z., Zhang, P., & Yan, Y. (2021) · International Symposium on Artificial Intelligence for Medicine Sciences (ISAIMS) · doi:10.1145/3500931.3500968 · Cited by 5
“Cambridge researchers [10] collected cough sounds from about 7000 individuals and more than 200 of whom were COVID-19 patients.”
BackgroundAn Audio Signal-based COVID-19 Detection Methodology using Modified DenseNet121
Saha, S., Bhadra, R., & Kar, S. (2021) · IEEE India Conference · doi:10.1109/indicon52576.2021.9691766 · Cited by 3
A Proposed WoT System for Diagnosing the Infection of Coronavirus (Covid-19)
Thair, D., & Ali, A. E. (2022) · Engineering and Technology Journal · doi:10.30684/etj.v40i4.2087 · Cited by 3
“This means it describes the lung auscultation in COVID-19 into an intelligent autonomous stethoscope benchmarked against the human expert perception[21].”
MethodCOVID-19 Detection Using Forced Cough Sounds and Medical Information
de Souza, L. A. M., Bernardino, H. S., de Souza, J. F., & Vieira, A. B. (2023) · Revista de Informática Teórica e Aplicada · doi:10.22456/2175-2745.126016 · Cited by 3
“[8] and [12] used their databases, collected online, while the first one is available through the”
BackgroundMethodInfluentialRahouma, K. H., Ramzy, S. M., & Aly, M. (2023) · Journal of Advanced Engineering Trends · doi:10.21608/jaet.2022.132552.1149 · Cited by 3
Automatic diagnosis of COVID-19 related respiratory diseases from speech
Shekhar, K., Chittaragi, N. B., & Koolagudi, S. G. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-14923-y · Cited by 3
“[5] tried to explore the area of automatic diagnosis of COVID-19, whose symptoms involve respiratory problems like coughing, breathlessness and/or erratic breathing.”
BackgroundMethodResultInfluentialCOVID-19 Detection from Speech in Noisy Conditions
Liu, S., Mallol-Ragolta, A., & Schuller, B. W. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10094304 · Cited by 3
“In this regard, previous works in the literature explored cough [1, 2], breath [3, 4], and speech [5, 6] signals for the detection of COVID-19 patients.”
The Design of a Cough Disease Classification System Using Cube-Transformer
Chen, Y., Hsu, C., & Yang, B.-X. (2023) · International Conference on Smart Applications, Communications and Networking (SmartNets) · doi:10.1109/smartnets58706.2023.10215518 · Cited by 3
FairComp: Workshop on Fairness and Robustness in Machine Learning for Ubiquitous Computing
Yfantidou, S., Spathis, D., Constantinides, M., Xia, T., & van Berkel, N. (2023) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/3594739.3605107 · Cited by 3
“Currently, we witness a surge in high-stakes applications such as diagnosing COVID-19 infections [1], detection of Atrial Fibrillation (AFib) [7], and enhancement of cognitive performance [3].”
BackgroundSelf-citationRivero, A. J. L., Corbacho, C. C., Romero-Arias, T., Martín-Merino, M., & Váz, P. (2024) · IEEE Access · doi:10.1109/access.2024.3487773 · Cited by 3
From lab to pocket: A novel continual learning-based mobile application for screening COVID-19
Falero, D., Kabir, M. A., & Homaira, N. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.112960 · Cited by 4
Detection and Diagnostic Approach of COVID-19 Based on Cough Sound Analysis
Al-Ani, M. S., Mohammed, T. S., Sultan, A. I., Sultan, H. I., Alheeti, K. M. A., & Aljebory, K. M. (2021) · Journal of Computer Science · doi:10.3844/jcssp.2021.580.597 · Cited by 3
“Brown et al. (2020) used a dataset of respiratory sounds that is collected to aid diagnosis of COVID-19.”
MethodDeep Learning Anomaly Detection methods to passively detect COVID-19 from Audio
Murthy, S. N., & Agu, E. (2021) · IEEE International Conference on Digital Health (ICDH) · doi:10.1109/icdh52753.2021.00023 · Cited by 4
Capabilities of computer analysis of breath sounds in patients with COVID-19
Фурман, Е. Г., Charushin, A. O., Eirikh, E., Furman, G. B., Sokolovsky, V., Malinin, S., Шелудько, В. С., Polyanskaya, D. A., Калинина, Н. М., & Shtivelman, D. (2021) · Perm Medical Journal · doi:10.17816/pmj38397-109 · Cited by 3
Screening of COVID-19 using Cough Audio Frequencies
(2021) · International Journal of Advanced Trends in Computer Science and Engineering · doi:10.30534/ijatcse/2021/511032021 · Cited by 3
Detection of Covid-19 from Joint Time and Frequency Analysis of Speech, Breathing and Cough Audio
Harvill, J. B., Wani, Y. R., Chatterjee, M., Alam, M., Beiser, D. G., Chestek, D. W., Hasegawa‐Johnson, M., & Ahuja, N. (2022) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp43922.2022.9746015 · Cited by 4
A novel infrasound and audible machine-learning approach to the diagnosis of COVID-19
Dori, G., Bachner-Hinenzon, N., Kasim, N., Zaidani, H., Perl, S. H., Maayan, S. L., Shneifi, A., Kian, Y., Tiosano, T., Adler, D., et al. (2022) · ERJ Open Research · doi:10.1183/23120541.00152-2022 · Cited by 3
Security of Healthcare Data Using Blockchains: A SurveyPreprint
Pandey, M., Agarwal, R., Shukla, S. K., & Verma, N. K. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.12326 · Cited by 6
“Further, as another example, in (Brown et al., 2020), the authors propose using smartphones to capture and analyze cough sounds for identifying potential infection with COVID-19.”
BackgroundMethodPersonal Data GentrificationPreprint
Herrera, J. L., Berrocal, J., García-Alonso, J. M., Murillo, J. M., Chen, H.-Y., Julien, C., Mäkitalo, N., & Mikkonen, T. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.17109 · Cited by 3
COVID-19 Detection Using Recorded Coughs in the 2021 DiCOVA ChallengePreprint
Elizalde, B., & Tompkins, D. G. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.10619 · Cited by 3
“Performances over 80% AUC are among the highest reported in the literature for COVID identification using cough recordings in this dataset and in other datasets [1, 7, 8, 9].”
BackgroundUsing Self-Supervised Feature Extractors with Attention for Automatic COVID-19 Detection from SpeechPreprint
Mendonça, J., Solera-Ureña, R., Abad, A., & Trancoso, I. M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.00112 · Cited by 3
“The imperative need for properly labeled datasets has been partially addressed by several initiatives, such as those conducted by the University of Cambridge [8, 9] and the Indian Institute of Science, Bangalore [10], besides our own on-going efforts at INESC-ID/IST-University of Lisbon 1 .”
The Dawn of the Human-Machine Era: A forecast of new and emerging language technologies
Sayers, D., Sousa‐Silva, R., Höhn, S., Ahmedi, L., Allkivi-Metsoja, K., Anastasiou, D., Beňuš, Š., Bowker, L., Bytyçi, E., Catalá, A., et al. (2021) · Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT) · doi:10.20381/ruor-27012 · Cited by 9
Intelligent Multi-Sensor System for Remote Detection of COVID-19
Zaz, G., Marktani, M. A., Elboushaki, A., Farhane, Y., Mechaqrane, A., Jorio, M., Hajji, B., Dosse, S. B., Mansouri, A., & Ahaitouf, A. (2022) · Advances in sustainability science and technology · doi:10.1007/978-981-16-9101-0_11 · Cited by 2
Acoustic and Clinical Data Analysis of Vocal Recordings: Pandemic Insights and Lessons
Martins, P., Paixão, P., Caires, I., Matias, P., Gamboa, H. F. S., Soares, F., Gómez‐Vilda, P., Sousa, J., & Neuparth, N. M. B. (2024) · Diagnostics · doi:10.3390/diagnostics14202273 · Cited by 2
“Brown et al. [10] proposed a machine learning (ML) pipeline that extracts features from audio recordings of coughing and breathing (from the COVID-19 Sounds database) and feeds them into a statistical model to distinguish between cases with COVID-19 and without COVID-19.”
MethodDiemaNet: An automated detection model for three typical respiratory diseases
Xie, J., Xie, L., Xiao, T., Zhu, R., Hu, C., Qian, K., & Zhang, C. (2025) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2025.108504 · Cited by 3
A-TBNet:attention-guided neural network for tuberculosis detection using cough audio signals
Sahu, G., Kumar, S., & Vidhu, N. P. (2026) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-026-03017-4 · Cited by 2
Liu, Z.-K., Bock, K. D. D., Zhang, L.-F., Wang, J., & Liang, L. (2026) · Annals of Operations Research · doi:10.1007/s10479-026-07264-0 · Cited by 2
“Brown et al. (2020) employed machine learning techniques to diagnose COVID-19 based on features extracted from cough and respiratory sounds.”
Cough biomarkers for diagnosis and monitoring of respiratory disease: a systematic review
Jinming, X., Kathiresan, T., Siddiqui, A., Mazzone, S. B., & Vogel, A. P. (2026) · European Respiratory Review · doi:10.1183/16000617.0288-2025 · Cited by 2
Sound-Based Respiratory Disease Recognition with Machine Learning
Xu, X. (2021) · Communications in computer and information science · doi:10.1007/978-981-16-8885-0_8 · Cited by 2
Effati, M., & Nejat, G. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-24670-8_20 · Cited by 2
Cough-based COVID-19 Detection with Multi-head Deep Neural Network
Gupta, R., Krishna, T. A., & Adeeb, M. (2022) · International Conference on Data Science, Agents & Artificial Intelligence (ICDSAAI) · doi:10.1109/icdsaai55433.2022.10028889 · Cited by 2
“Cough sound have been recorded using microphone of computer and smartphones [9, 10, 11].”
MethodThe Nexus between Digital Innovation and Digital Entrepreneurship in the Strategic Transformation
Tangri, K., Kalra, D., Katuse, P., Masaeid, T. F. A., & Afifi, M. A. M. (2023) · International Conference on Business Analytics for Technology and Security (ICBATS) · doi:10.1109/icbats57792.2023.10111410 · Cited by 2
“strategies to modify and challenge established business paradigms, resulting in higher production, efficiency, and competitiveness [1], [2].”
BackgroundFaezipour, M., Faezipour, M., & Pourreza, S. (2023) · Sustainability · doi:10.3390/su151813832 · Cited by 2
Ekiz, A., & Kaplan, K. (2023) · Innovations in Intelligent Systems and Applications Conference (ASYU) · doi:10.1109/asyu58738.2023.10296675 · Cited by 2
“Manzella and Pagliarini et al. (2023) [11] proposed an automated classification as a multivariate time series by using interval temporal decision trees and forests on the crowdsourced dataset that compiled by researchers at the University of Cambridge[12].”
BackgroundMethodInfluentialAnalysing Breathing Patterns in Reading and Spontaneous Speech
Deshpande, G., Schuller, B. W., Deshpande, P. D., Joshi, A. R., Oza, S. K., & Patel, S. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-48312-7_1 · Cited by 2
Kim, J., & Lee, J. (2024) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc53108.2024.10781593 · Cited by 2
“For this study, we utilized three cough data sets named Cambridge, Coswara, and Virufy [4]–[6].”
The worldwide methods of artificial intelligence for detection and diagnosis of COVID-19
Eldow, M. E. Y. (2021) · Elsevier eBooks · doi:10.1016/b978-0-323-89777-8.00012-9 · Cited by 4
“In order to diagnose the disease via coughs and breathing, a binary machine learning classifier is used in Brown et al. (2020). The refined records of cough and breaths consist of 141 samples of patients who declared having tested positive of COVID-19 and the control sets of non-COVID-19 consist of 298 samples (report…”
InfluentialAn Ensemble Approach for the Diagnosis of COVID-19 from Speech and Cough Sounds
Fathan, A., Alam, J., & Kang, W. H. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-87802-3_18 · Cited by 2
A Novel Graph Indexing Approach for Uncovering Potential COVID-19 Transmission Clusters
Zhu, X., Huang, X. S., Sun, L., & Liu, J. (2022) · ACM Transactions on Knowledge Discovery from Data · doi:10.1145/3538492 · Cited by 2
“Recently, many studies have been conducted on COVID-19 research [1, 5, 9, 16, 18, 24, 37], including quantifying the underlying transmission patterns of COVID-19 outbreak [25], security-aware mobile tracking system [34], forecasting [1, 37], and data privacy [30].”
BackgroundAn Improved Technique for Preliminary Diagnosis of COVID-19 via Cough Audio Analysis
Pandhi, T., Kapoor, T., & Gupta, B. (2022) · Communications in computer and information science · doi:10.1007/978-3-031-07005-1_30 · Cited by 2
Lane, J. M., Moody, A. B., Yau, Y., & Mankin, R. W. (2022) · Springer eBooks · doi:10.1007/978-981-16-4445-0_20 · Cited by 3
Ren, Z. X., Chang, Y., Nejdl, W., & Schuller, B. W. (2022) · Acta Acustica · doi:10.1051/aacus/2022029 · Cited by 2
Mohammed, T. S., Sultan, A. I., Alheeti, K. M. A., Aljebory, K. M., Sultan, H. I., & Al-Ani, M. S. (2022) · Baghdad Science Journal · doi:10.21123/bsj.2022.6516 · Cited by 2
Asiaee, M., Nourbakhsh, M., Vahedian‐Azimi, A., Zare, M., Jafari, R., Atashi, S. S., & Keramatfar, A. (2023) · Clinical Linguistics & Phonetics · doi:10.1080/02699206.2022.2160659 · Cited by 2
“Specifically in the field of artificial intelligence, voice and cough-related measures have been developed (Brown et al., 2020; Laguarta et al., 2020; Sharma et al., 2020; Topol, 2020; Vahedian-Azimi et al., 2021).”
BackgroundArtificial intelligence in COVID-19
Nessiem, M. A., Coppock, H., Mohamed, M. M., & Schuller, B. W. (2023) · Elsevier eBooks · doi:10.1016/b978-0-323-91794-0.00016-0 · Cited by 3
CNN-based Diagnosis System on Skin Cancer using Ensemble Method Weighted by Cubic PrecisionPreprint
Jiang, P. (2021) · doi:10.36227/techrxiv.16964893.v1 · Cited by 2
Comparative Analysis of COVID 19 Detection from Cough Speech Using Machine Learning Classifiers
Mishra, S., Dash, T. K., Panda, G., Kumar, A., & Singh, S. K. (2022) · Communications in computer and information science · doi:10.1007/978-3-031-23233-6_30 · Cited by 1
Cough Detection for Prevention Against the COVID-19 Pandemic
Bouzammour, B., Zaz, G., Marktani, M. A., Ahaitouf, A., & Jorio, M. (2023) · Lecture notes in electrical engineering · doi:10.1007/978-981-19-6223-3_46 · Cited by 1
Pradhan, J. D., Prasad, L. V. N., Dash, T. K., Guduri, M., & Panda, G. (2024) · Journal of Artificial Intelligence and Technology · doi:10.37965/jait.2023.0435 · Cited by 1
“For the study of COVID-19, Five datasets have been used including Coswara (Dataset-2) [29], Crowd-sourced University of Cambridge (Dataset-3) [30], Virufy (Dataset-4) [31], recorded interviews from online platforms in telephone quality speech (Dataset-5) [32], Coughvid (Dataset-6) [33].”
MethodMoffo, F. M., Woguia, A. V. N., Bowong, S., & Ngono, J. M. (2024) · Communications in computer and information science · doi:10.1007/978-3-031-63110-8_3 · Cited by 1
Moffo, F. M., Woguia, A. V. N., Ngono, J. M., & Bowong, S. (2025) · Revue Africaine de la Recherche en Informatique et Mathématiques Appliquées · doi:10.46298/arima.13343 · Cited by 1
Cai, R., Li, W., Han, L., Chen, J., Zou, D., Chen, X., Pan, Y., Feng, L., & Qi, J. (2024) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm62325.2024.10821829 · Cited by 1
COVID-19 Detection from Cough Sound Signal using Random Forest Learning of Deep Spectral Features
Puja, W. D., Sultana, S., & Hossain, A. B. M. A. (2024) · IEEE International Conference on Signal Processing, Information, Communication and Systems (SPICSCON) · doi:10.1109/spicscon64195.2024.10940971 · Cited by 2
“Among the acoustic properties, Brown et al. [7] used the sounds of breathing and coughing, where the dominating features are RMS energy, roll-off frequencies, spectral centroid, zero-crossing rate, MFCC, duration onsets, tempo, and period.”
Sonti, N., Rukmini, M. S. S., & Munagala, V. (2025) · International Journal of Image Graphics and Signal Processing · doi:10.5815/ijigsp.2025.02.03 · Cited by 1
Healthcare-Associated Infection Prediction on Hospitalized COVID-19 Patients
Lopes, F. L., Ferreira, P. R. A., & Lorena, A. C. (2025) · World Congress on Medical Physics and Biomedical Engineering, September 7 - 12, 2009, Munich, Germany · doi:10.1007/978-3-031-94934-0_7 · Cited by 1
CoughViT: A Self-Supervised Vision Transformer for Cough Audio Representation Learning
Luong, J., Xue, H., & Salim, F. D. (2025) · ACM International Symposium on Wearable Computers (ISWC) · doi:10.1145/3715071.3750404 · Cited by 1
“Researchers have demonstrated the ability to train classifiers to effectively detect diseases such as Asthma [2], Bronchitis [35], and COVID-19 [6] using cough audio.”
Kaushik, P., Bhutani, M., & Bhagat, K. M. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-032-02949-2_18 · Cited by 1
Aquino-García, A. M., Pérez-Espinosa, H., Andreu-Pérez, J., & Rodríguez‐González, A. Y. (2026) · Machine Learning and Knowledge Extraction · doi:10.3390/make8030080 · Cited by 1
“Advances in information and communications technologies (ICT) have enabled non-invasive, cost-effective systems for respiratory disease detection via automated cough analysis [1–4].”
Ayappan, G., Sumathi, S., Mani, V., & Jebarani, P. E. (2026) · Scientific Reports · doi:10.1038/s41598-026-44936-0 · Cited by 1
Dhekane, S., Agrawal, V., Datta, A. A., & Kulkarni, K. (2021) · Advances in intelligent systems and computing · doi:10.1007/978-981-16-2008-9_13 · Cited by 1
Toward Voice Detection for Screening Rheumatology Patients
Aharonov, O. (2021) · Indian Journal of Rheumatology · doi:10.4103/injr.injr_27_21 · Cited by 1
Narayanaswamy, V., Spanias, P., Rao, S., & Spanias, A. (2021) · IEEE Frontiers in Education Conference (FIE) · doi:10.1109/fie49875.2021.9637430 · Cited by 1
A prototype deep learning system for the acoustic monitoring of intensive care patients
Lykartsis, A., Hädrich, M., & Weinzierl, S. (2021) · European Signal Processing Conference (EUSIPCO) · doi:10.23919/eusipco54536.2021.9616347 · Cited by 1
“…as coughing or breathing, with high accuracy [7]; by crowdsourcing patient data and comparing respiratory sounds to those of healthy individuals, [8] could use transfer learning and basic audio features to reach an Area-Under-Curve (AUC) higher than 80% ; and fully combined software and mobile…”
BackgroundNutzung von künstlicher Intelligenz zur Bekämpfung der COVID-19-Pandemie
Fritsch, S. J., Sharafutdinov, K., Schuppert, A., & Bickenbach, J. (2022) · AINS - Anästhesiologie · Intensivmedizin · Notfallmedizin · Schmerztherapie · doi:10.1055/a-1423-8039 · Cited by 1
Advanced Medical Images Recognition and Diagnosis of Respiratory System Viruses
Tayel, M. B., Fahaar, A. E., & Fahmy, A. (2022) · International Convention on Information and Communication Technology, Electronics and Microelectronics · doi:10.23919/mipro55190.2022.9803702 · Cited by 1
Machine learning models to characterize the cough signal of patients with COVID-19
Salamea, C., Sánchez, T., Calderón, X. A., Guaña, J., Castañeda, P., & Reina, J. (2022) · LACCEI International Multi-Conference for Engineering, Education and Technology (LACCEI) · doi:10.18687/laccei2022.1.1.145 · Cited by 1
Application of machine learning in the fight against the COVID-19 pandemic: A review
Čolaković, A., Avdagić-Golub, E., Begović, M., Memić, B., & Hasković-Džubur, A. (2022) · Acta Facultatis Medicae Naissensis · doi:10.5937/afmnai39-38354 · Cited by 1
Isiaka, R. M., Babatunde, R. S., Ajao, J. F., Yusuff, S. R., Popoola, D. D., AROWOLO, M. O., & Adewole, K. S. (2022) · Advances in Multidisciplinary & Scientific Research Journal Publication · doi:10.22624/aims/maths/v10n4p2 · Cited by 6
Identification of Covid-19 Using Speech Recognition and Convolutional Neural Networks
Ranaweera, T., & Karunanayaka, K. T. (2023) · International Conference on Advanced Research in Computing (ICARC) · doi:10.1109/icarc57651.2023.10145735 · Cited by 1
“A cross-sectional approach between vocal cords (coughing and breathing) was developed by researchers at the University of Cambridge [10] in order to find covid-19 patients.”
MethodMethods of Machine Learning in Epidemic Risk Assessment: The Case of the Covid-19
Deshmukh, S., & Kaur, S. (2023) · International Conference for Emerging Technology (INCET) · doi:10.1109/incet57972.2023.10170075 · Cited by 1
“Research Collaboratory for Structural Bioinformatics (RCSB) and Global Health Drug Discovery Institute (GHDDI) datasets analyze the structures of RNA, spike proteins, and other biological molecules[12].”
BackgroundKanumuri, C., & Madhavi, C. H. R. (2023) · AIP conference proceedings · doi:10.1063/5.0148900 · Cited by 1
Evolutionary Explainable Rule Extraction from (Modal) Random Forests
Ghiotti, M., Manzella, F., Pagliarini, G., Sciavicco, G., & Stan, I. E. (2023) · Frontiers in artificial intelligence and applications · doi:10.3233/faia230350 · Cited by 1
Hussan, P. H., & Ali, I. H. (2024) · AIP conference proceedings · doi:10.1063/5.0191721 · Cited by 1
Meegahapola, L., Spathis, D., Constantinides, M., Zhang, H., Yfantidou, S., van Berkel, N., & Dey, A. K. (2024) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/3675094.3677572 · Cited by 1
“Currently, we witness a surge in high-stakes applications such as diagnosing COVID-19 infections [2], detection of Atrial Fibrillation (AFib) [9], and enhancement of cognitive performance [4].”
Self-citationDiagnosis Through Adventitious Sounds Detection and Respiratory Phases Identification Using XGBoost
Mitsuke, T., Shimakawa, H., & Harada, F. (2024) · International Conference on Frontiers of Signal Processing (ICFSP) · doi:10.1109/icfsp62546.2024.10785273 · Cited by 1
Harnessing the Power of Vocal Signals in COVID-19 Detection Utilizing Machine Learning
Mann, A., Jadhav, A. P., Matovu, R., & Gupta, V. (2024) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata62323.2024.10825050 · Cited by 1
She, J., Shi, L., Li, P., Dong, Z., Li, R., Li, S., Gu, L., Tong, Z., Yang, Z., Ji, Y.-J., et al. (2025) · Digital Health · doi:10.1177/20552076251339284 · Cited by 2
“These results align with recent studies on acoustic signal analysis, which highlight the importance of selecting relevant features and reducing dimensionality for improving the efficiency of machine learning models in health diagnostics[30, 31, 32].”
SRIB Submission to Interspeech 2021 DiCOVA ChallengePreprint
Singh, V. P., Kumar, S., Jha, R. S., & Pandey, A. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.07972 · Cited by 1
“Examples include the ‘Coughvid’ [7], ‘Breath for Science’ [8], ‘Coswara’ [9], and ‘CoughAgainstCovid’[10].”
Kelley, K., Kelley, M., Kelley, S. C., Sakara, A. A., & Ramírez, M. A. S. (2021) · medRxiv · doi:10.1101/2021.11.13.21266289 · Cited by 1
TinyM²Net: A Flexible System Algorithm Co-designed Multimodal Learning Framework for Tiny DevicesPreprint
Rashid, H.-A., Ovi, P. R., Gangopadhyay, A., & Mohsenin, T. (2022) · PubMed Central · doi:10.13016/m2k9xf-fqm5 · Cited by 1
Human Respiratory Sound Classification for Remote Health Monitoring Applications
Cohen-McFarlane, M. (2022) · Carleton University's Institutional Repository (MacOdrum Library, Carleton University) · doi:10.22215/etd/2022-15017 · Cited by 2
Cmbatting COVID-19: Artificial Intelligence Technologies & ChallengesPreprint
Patel, N., Trivedi, S., & Chatterjee, J. M. (2022) · doi:10.14293/s2199-1006.1.sor-.ppvk63o.v1 · Cited by 3
Application of Speech-Derived Breathing Patterns in Detecting Respiratory DisordersPreprint
Deshpande, G., & Schuller, B. W. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4611035 · Cited by 1
Audio Texture Analysis of Biomedical Audio Signals
Sharma, G. (2024) · doi:10.32920/26871325 · Cited by 1
Leiva, K. M. R., Gupta, A. R., Grosmaire, A., Procházková, S., Matouch, P., Závacká, I., Skroch, J., & Černý, M. (2026) · Scientific Data · doi:10.1038/s41597-025-06449-9 · Cited by 1
“This dataset will significantly improve algorithm development and training protocols and, will ensure more reliability for end-user solutions 19,20 .”
ML-Enabled Informed Intervention for Crowdsourcing-Based Optimization of Medical Resources
Siddavatam, I. N. A., Dalvi, A., Patel, A., Panchal, A., Vedpathak, A., & Thakkar, V. (2021) · Advances in healthcare information systems and administration book series · doi:10.4018/978-1-7998-7709-7.ch017
A Three-Fold Machine Learning Approach for Detection of COVID-19 from Audio Data
Kumar, N., Mittal, V., & Sharma, Y. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-86970-0_35
Kelley, K., Sakara, A. A., Kelley, M., Kelley, S. C., McLenaghan, P., Aldir, R., Cox, M., Donaldson, N., Stogsdill, A., Kotchou, S., et al. (2021) · medRxiv · doi:10.1101/2021.11.12.21266271
A Novel Coronavirus Speech Dataset: CoSDa
Yılmaz, G., Tektaş, R., Kazan, M. S., Ndigande, A. P., & Pehlivanoğlu, M. K. (2021) · Innovations in Intelligent Systems and Applications Conference (ASYU) · doi:10.1109/asyu52992.2021.9598944
Metadata
- Authors
- Brown, C., Chauhan, J., Grammenos, A., Han, J., Hasthanasombat, A., Spathis, D., Xia, T., Cicuta, P., & Mascolo, C.
- Affiliations
- University of Cambridge (GB)
- University of Cambridge, Cambridge, United Kingdom
- ORCID
- Venue
- Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining
- Publisher
- ACM
- Published
- 2020-08-20
- Pages
- 3474-3484
- OpenAlex
- W3035378948
- Cited by
- 447
- References
- 34
- Citations by year
- 2026: 17 · 2025: 26 · 2024: 49 · 2023: 78 · 2022: 124 · 2021: 136 · 2020: 15
- FWCI
- 253.82
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- Cambridge University Engineering Department Publications Database (submittedVersion)
- Apollo (University of Cambridge) (submittedVersion, cc-by)
- arXiv (Cornell University)
- Apollo (cc-by)
- Funders
- Cystic Fibrosis Trust
- European Research Council (833296)
- Topics
- Health Sciences › Medicine › Pulmonary and Respiratory Medicine › Phonocardiography and Auscultation Techniques
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › COVID-19 diagnosis using AI
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Keywords
- COVID-19 diagnosis, lung sounds, cough, digital stethoscope, asthma, binary classification, prescreening
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.