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 201–300 of 493
VAP: Online Data Valuation and Pricing for Machine Learning Models in Mobile Health
Xu, A., Zheng, Z., Li, Q., Wu, F., & Chen, G. (2023) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2023.3316145 · Cited by 13
“Recently, researchers are making recent progress in COVID-19 [7], [57], [58], [59].”
Time-Frequency Scattergrams for Biomedical Audio Signal Representation and Classification
Sharma, G., Umapathy, K., & Krishnan, S. (2023) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2023.3332544 · Cited by 11
Voice EHR: introducing multimodal audio data for health
Anibal, J., Huth, H. B., Li, M., Hazen, L., Daoud, V., Ebedes, D. M., Yen, L. M., Nguyen, H. T. T., Hong, P. V., Kleinman, M., et al. (2025) · Frontiers in Digital Health · doi:10.3389/fdgth.2024.1448351 · Cited by 12
Performance Comparison of Apache Hadoop and Apache Spark for COVID-19 data sets
George, M. M., & Rasmi, P. S. (2022) · International Conference on Smart Systems and Inventive Technology (ICSSIT) · doi:10.1109/icssit53264.2022.9716232 · Cited by 10
“The authors [23] proposed a website and Android app to distinguish a COVID-19 cough sound from other respiratory sounds with the help of input data from about 7000 unique users.”
BackgroundL3-Net Deep Audio Embeddings to Improve COVID-19 Detection from Smartphone Data
Campana, M. G., Rovati, A., Delmastro, F., & Pagani, E. (2022) · IEEE International Conference on Smart Computing · doi:10.1109/smartcomp55677.2022.00029 · Cited by 12
The Use of Audio Signals for Detecting COVID-19: A Systematic Review
Aleixandre, J. G., Elgendi, M., & Menon, C. (2022) · Sensors · doi:10.3390/s22218114 · Cited by 10
“2021 Milaniet al. [42] Coswara [V] (NR) NR (NR) Silence removal GTCC (NR) k-NN, BT NR NR 90.9 90.0 NR 2021 Nelloreet al. [44] Coswara [C] (1273) NR (NR) Silence removal FBC (128×3), F0, Fn (4), RMS FNN 34.3 85.6 NR NR 65.7 2021 Paharet al. [41] Coswara, Cambridge, Sarcos [C] (1171, 517, 44) NR (Cos.: 44.1 kHz, Cam.”
MethodInfluentialGrant, D., McLane, I. M., Rennoll, V., & West, J. E. (2022) · Sensors · doi:10.3390/s22239530 · Cited by 12
“NeurIPS 2021 Dataset The NeurIPS 2021 Dataset includes crowdsourced cough and breathing sound recordings collected by the University of Cambridge and released for scientific exploration [31].”
Dang, T., Han, J., Xia, T., Bondareva, E., Brown, C., Chauhan, J., Grammenos, A., Spathis, D., Cicuta, P., & Mascolo, C. (2023) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3580305.3599792 · Cited by 20
“Instead of training the model to forecast future values given limited past samples, the model is trained on interpolation tasks, where a subset of the audio samples in the sequence are randomly selected as context vectors and the entire sequence is used as the target vectors, following conventional choices in [3] and…”
BackgroundMethodSelf-citationCough Sound based COVID-19 Detection with Stacked Ensemble Model
Gupta, R., Krishna, T. A., & Adeeb, M. (2022) · International Conference on Smart Systems and Inventive Technology (ICSSIT) · doi:10.1109/icssit53264.2022.9716373 · Cited by 10
“They obtained an AUC of 0.876 on Cambridge dataset [10] and 0.771 on Coswara dataset [5].”
BackgroundMethodInfluentialRashid, H.-A., Sajadi, M. M., & Mohsenin, T. (2022) · IEEE Healthcare Innovations and Point of Care Technologies Conference (HI-POCT) · doi:10.1109/hi-poct54491.2022.9744064 · Cited by 10
“[16], [20] provides their dataset upon signing their user agreement.”
BackgroundCOVID-19 classification using thermal images
Canales-Fiscal, M. R., Treviño, V., Ramírez-Treviño, L. J., Ortíz-López, R., Cardona‐Huerta, S., Díaz, V. J. L., & Tamez‐Peña, J. G. (2022) · Journal of Biomedical Optics · doi:10.1117/1.jbo.27.5.056003 · Cited by 10
“Particular respiratory patterns were analyzed in individuals that tested positive for COVID-19, in contrast to healthy individuals and individuals with asthma, and they were found to be distinguishable (AUC of above 80%).(19) In addition, studies show that pulmonary and laryngeal involvements in people with COVID-19 c…”
BackgroundTinyM2Net: A Flexible System Algorithm Co-designed Multimodal Learning Framework for Tiny DevicesPreprint
Rashid, H.-A., Ovi, P. R., Busart, C., Gangopadhyay, A., & Mohsenin, T. (2022) · OSF Preprints (OSF Preprints) · doi:10.31219/osf.io/e8px7 · Cited by 10
A large-scale and PCR-referenced vocal audio dataset for COVID-19
Budd, J., Baker, K., Karoune, E., Coppock, H., Patel, S., Payne, R., Cañadas, A. T., Titcomb, A., Hurley, D., Egglestone, S., et al. (2024) · Scientific Data · doi:10.1038/s41597-024-03492-w · Cited by 15
“To facilitate independent validation of existing models, audio samples common across existing studies were collected in the online survey, including: volitional (forced) cough, an exhalation sound, and speech.”
Fused Audio Instance and Representation for Respiratory Disease Detection
Truong, T., Lenga, M., Serrurier, A., & Mohammadi, S. (2024) · Sensors · doi:10.3390/s24196176 · Cited by 10
Shokouhmand, S., Bhatt, S., & Faezipour, M. (2025) · Electronics · doi:10.3390/electronics14101994 · Cited by 9
Mobile medical systems for equitable healthcare
Chan, J., Goel, M., Gollakota, S., & Nandakumar, R. (2025) · Nature Reviews Bioengineering · doi:10.1038/s44222-025-00330-5 · Cited by 11
Screening COVID-19 by Swaasa AI platform using cough sounds: a cross-sectional study
Pentakota, P., Rudraraju, G., Sripada, N. R., Mamidgi, B., Gottipulla, C., Jalukuru, C., Palreddy, S. D., Bhoge, N. K. R., Firmal, P., Yechuri, V., et al. (2023) · Scientific Reports · doi:10.1038/s41598-023-45104-4 · Cited by 10
“They highlighted that how a simple binary machine-learning classifier can distinguish COVID-19 cough sounds from healthy subjects by achieving an overall AUC of above 80% 41 .”
BackgroundResultIslam, M. S., Hasan, K. F., Shajeeb, H. H., Rana, H. K., Rahman, M. S., Hasan, M. M., Azad, A., Abdullah, I., & Moni, M. A. (2025) · AI Open · doi:10.1016/j.aiopen.2025.01.003 · Cited by 10
Transformer-based CNNs: Mining Temporal Context Information for Multi-sound COVID-19 Diagnosis
Chang, Y., Ren, Z. X., & Schuller, B. W. (2021) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc46164.2021.9629552 · Cited by 10
Matias, P., Costa, J. G. C., Carreiro, A. V., Gamboa, H. F. S., Sousa, I., Gomez, P., Sousa, J., Neuparth, N. M. B., Martins, P., & Soares, F. (2022) · IEEE Access · doi:10.1109/access.2022.3211295 · Cited by 9
“As COVID-19 Sounds dataset already undergoes an audio quality check (through an automatic tool) [18], the quality of the provided audio files is assumed to be good enough for analysis.”
MethodInfluentialJillahi, K. B., & Iorliam, A. (2024) · Journal of Computing Theories and Applications · doi:10.62411/jcta.10350 · Cited by 10
“In [43], a binary ML classifier is proposed to diagnose COVID-19 using only cough and breathing patterns data.”
MethodCOVID-19 Classification Using Cough Sounds
Rahman, D. A., & Lestari, D. P. (2021) · International Conference on Advanced Informatics: Concepts, Theory and Applications (ICAICTA) · doi:10.1109/icaicta53211.2021.9640278 · Cited by 10
Ayappan, G., & Anila, S. (2023) · Cybernetics & Systems · doi:10.1080/01969722.2023.2166244 · Cited by 9
“Cough and respiratory sounds have been found to be 82% accurate in diagnosing COVID-19 (Brown et al. 2020).”
BackgroundHussain, S., Amran, G. A., Alabrah, A. A., Alkhalil, L., & AL-Bakhrani, A. A. (2024) · IEEE Access · doi:10.1109/access.2024.3521938 · Cited by 12
Das, S., Nag, A., Adhikary, D., Ram, R. J., Aravind, B., Ojha, S. K., & Hegde, G. M. (2021) · IEEE India Conference · doi:10.1109/indicon52576.2021.9691485 · Cited by 8
Kosar, A., Asif, M., Ahmad, M. B., Akram, W., Mahmood, K., & Kumari, S. (2024) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2024.102858 · Cited by 8
A Comprehensive Review on COVID-19 Detection Based on Cough Sounds, Symptoms, CXR, and CT Images
Mahanty, C., Patro, S. G. K., Rathor, S., Rachapudi, V., Mohanty, J., Muzammil, K., Islam, S., & Khan, W. A. (2024) · IEEE Access · doi:10.1109/access.2024.3396728 · Cited by 9
“Brown et al. [12] suggested utilizing breathing and cough noises to identify Covid-19 utilizing crowdsourced dataset.”
MethodMASC: Wearable Design for Infectious Disease Detection Through Machine Learning
Mila, S. A., Ravi, B. B. Y., Kabir, M. R., & Ray, S. (2025) · IEEE Access · doi:10.1109/access.2025.3538518 · Cited by 11
Karas, V., & Schuller, B. W. (2021) · Interspeech (USB) · doi:10.21437/interspeech.2021-1267 · Cited by 8
“[12] used MFCCs with features extracted from Mel-spectrograms by a pretrained CNN to detect Covid-19 from coughing and breathing sounds gathered from a crowd-sourced dataset.”
BackgroundMethodSpeaking Corona? Human and Machine Recognition of COVID-19 from Voice
Hecker, P., Pokorny, F. B., Bartl-Pokorny, K. D., Reichel, U. D., Ren, Z. X., Hantke, S., Eyben, F., Schuller, D., Bert Arnrich, A., & Schuller, B. W. (2021) · Interspeech (USB) · doi:10.21437/interspeech.2021-1771 · Cited by 8
“Several research groups in the domain of computational paralinguistics have focused their efforts on collecting large ‘crowdsourced’ datasets (e.g., [17, 18, 19, 20]) using them to create machine learning models (e.g., [21, 22, 23, 24, 25, 26]).”
BackgroundDeep Learning-based Decision Support System for classification of COVID-19 and Pneumonia patients
Khan, M. U., Saeed, Z., Raza, A., Abbasi, Z. A., Ali, S. Z.-E.-Z., & Khan, H. (2022) · JAREE (Journal on Advanced Research in Electrical Engineering) · doi:10.12962/jaree.v6i1.229 · Cited by 8
“Cough sounds have been used in multiple investigations for sound-based medical diagnosis of Covid-19 [11, 13-16].”
MethodInfluentialDeep Learning Based Intelligent Classification Of Covid-19 & Pneumonia Using Cough Auscultations
Naqvi, S. Z. H., Khan, M. U., Raza, A., Saeed, Z., Abbasi, Z. A., & Ali, S. Z.-E.-Z. (2021) · International Multi-Topic ICT Conference (IMTIC) · doi:10.1109/imtic53841.2021.9719740 · Cited by 8
Tuncer, T., Akbal, E., Aydemir, E., Belhouari, S. B., & Doğan, Ş. (2021) · European Journal of Technic · doi:10.36222/ejt.986599 · Cited by 8
COVID-19 Detection using Audio Spectral Features and Machine Learning
Esposito, M., Rao, S., Narayanaswamy, V., & Spanias, A. (2021) · Asilomar Conference on Signals, Systems and Computers (ACSSC) · doi:10.1109/ieeeconf53345.2021.9723323 · Cited by 9
Detecting Cough Recordings in Crowdsourced Data Using CNN-RNN
Sharan, R. V., Xiong, H., & Berkovsky, S. (2022) · IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI ...) · doi:10.1109/bhi56158.2022.9926896 · Cited by 9
“Several groups around the world have studied the cough sound of COVID-19, as a possible screening tool for this respiratory disease [4-6].”
BackgroundMethodContrastive Learning of Cough Descriptors for Automatic COVID-19 Preliminary Diagnosis
Bhosale, S., Tiwari, U., Chakraborty, R., & Kopparapu, S. K. (2021) · Interspeech (USB) · doi:10.21437/interspeech.2021-1249 · Cited by 10
“The usage of these features are well studied in previous works on cough sound detection [20, 9, 18, 31, 32].”
BackgroundAcoustic COVID-19 Detection Using Multiple Instance Learning
Reiter, M., & Pernkopf, F. (2024) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2024.3474975 · Cited by 7
Voice processing for COVID-19 scanning and prognostic indicator
Sondhi, S., Salhan, A. K., Santoso, C. A., Doucoure, M., Dharmawan, D. M., Sureka, A., Natasha, B. N., Danusaputro, A. D., Dowson, N. S., Yap, M. S. L., et al. (2021) · Heliyon · doi:10.1016/j.heliyon.2021.e08134 · Cited by 8
“Science, India [40] and Crowdsourced Respiratory Sound Data (DB-2) developed by Cambridge University, the UK [41].”
Evaluation of Respiratory Sounds Using Image-Based Approaches for Health Measurement Applications
Cohen-McFarlane, M., Xi, P., Wallace, B., Habashy, K., Huq, S., Goubran, R. A., & Knoefel, F. D. (2022) · IEEE Open Journal of Engineering in Medicine and Biology · doi:10.1109/ojemb.2022.3202435 · Cited by 7
Shati, A., Hassan, G. M., & Datta, A. (2023) · IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom) · doi:10.1109/trustcom60117.2023.00377 · Cited by 7
“They extracted time and frequency domain features from audio signals and then applied binary ML classifiers such as SVM, KNN, and Brown et al. [6] collected cough and breathing data using a website and Android app to discriminate between healthy, COVID-19, and asthma patients.”
MethodFRuDA: Framework for Distributed Adversarial Domain Adaptation
Gan, S., Mathur, A., Isopoussu, A., Kawsar, F., Bianchi‐Berthouze, N., & Lane, N. D. (2021) · IEEE Transactions on Parallel and Distributed Systems · doi:10.1109/tpds.2021.3136673 · Cited by 10
“As an example, let us consider the task of developing personalized health monitoring solutions on mobile devices, such as the prediction of COVID-19 from cough sounds collected from a smartphone [9].”
MethodA Deep Learning Approach to Predict COVID-19 Through Cough Analysis Using CNN-BiDirectional LSTM
Yalamanchili, B., Sree Deeksha., B., Sohan., V., Ajay., D., & Eshwar Sai Ram, M. (2022) · International Conference for Advancement in Technology (ICONAT) · doi:10.1109/iconat53423.2022.9726067 · Cited by 7
“Chloe Brown et al. proposed that simple machine learning algorithms can be used to detect Covid-19 using sound analysis[9].”
MethodAutoencoders and Ensemble-Based Solution for COVID-19 Diagnosis from Cough Sound
Hamdi, S., Moussaouı, A., Oussalah, M., & Saidi, M. (2022) · Lecture notes in networks and systems · doi:10.1007/978-3-031-18516-8_20 · Cited by 7
An evolutionary ensemble learning for diagnosing COVID-19 via cough signals
Najaran, M. H. T. (2023) · Intelligent Medicine · doi:10.1016/j.imed.2023.01.001 · Cited by 7
“In [19], cough and breathing signals are collected and processed to identify the positive cases.”
BackgroundA COUGH-BASED COVID-19 DETECTION SYSTEM USING PCA AND MACHINE LEARNING CLASSIFIERS
Benmalek, E., Mhamdi, J. E., Jilbab, A., & Jbari, A. (2022) · Applied Computer Science · doi:10.35784/acs-2022-31 · Cited by 7
Botonis, O. K., Mendley, J., Aalla, S., Veit, N. C., Fanton, M., Lee, J. Y., Tripathi, V., Pandi, V., Khobragade, A., Chaudhary, S. K., et al. (2024) · npj Digital Medicine · doi:10.1038/s41746-024-01287-2 · Cited by 7
“Vibratory movements of the lung have been correlated to diagnosis of COVID-19 infection 82,83 .”
BackgroundGanitidis, T., Αθανασίου, Μ., Mitsis, K., Zarkogianni, K., & Nikita, K. S. (2025) · Journal of Medical Internet Research · doi:10.2196/66919 · Cited by 7
The DiCOVA 2021 Challenge — An Encoder-Decoder Approach for COVID-19 Recognition from Coughing Audio
Deshpande, G., & Schuller, B. W. (2021) · Interspeech (USB) · doi:10.21437/interspeech.2021-811 · Cited by 14
“The COVID-19 detection (from non-COVID-19 asthmatic cough) performance reported by Cambridge University 7 in [1] states an Area Under the Curve (AUC) of 0 .”
BackgroundMethodInfluentialCovidEnvelope: An Automated Fast Approach to Diagnose COVID-19 from Cough Signals
Hossain, M. Z., Uddin, M. B., Yang, Y., & Ahmed, K. A. (2021) · IEEE Asia-Pacific Conference on Computer Science and Data Engineering (CSDE) · doi:10.1109/csde53843.2021.9718501 · Cited by 8
Costa, A., & Milne, R. (2022) · Big Data & Society · doi:10.1177/20539517221091138 · Cited by 7
“, 2020), voice analysis (Brown et al., 2020), or combinations of heart rate, sleep and activity data collected by digital devices (Quer et al.”
BackgroundMulti-modal approach for COVID-19 detection using coughs and self-reported symptoms
Nguyen-Trong, K., & Nguyen-Hoang, K. (2022) · Journal of Intelligent & Fuzzy Systems · doi:10.3233/jifs-222863 · Cited by 8
“A In contrast with the work of Chetupalli et al. [9], which used an equal weighting function for the fusion of modalities, this method employed different weights for each symp-226 tom. u For example, Chetu-204 palli et al. [9] proposed a multi-modal method using the Coswara dataset [ on the Cambridge dataset [7].”
MethodDas, S., Nag, A., Adhikary, D., Ram, R. J., Aravind, B., Ojha, S. K., & Hegde, G. M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.10891 · Cited by 9
“This has set the stage for developing myriad Artificial Intelligence (AI)-based applications to aid healthcare providers [1] including epidemiological modeling, patient triaging [2], and detecting infected subjects from chest X-rays or CT scans, or using cough sounds [3] or abnormal respiratory patterns [4].”
BackgroundXiong, H., Berkovsky, S., Kâafar, M. A., Jaffé, A., Coiera, E. W., & Sharan, R. V. (2022) · Scientific Reports · doi:10.1038/s41598-022-26492-5 · Cited by 6
“Considering the AUC scores, we observe the deep learning methods, CA-CNN and CNN-RNN, do not perform better than statistical methods.”
MethodEfficient Pandemic Infection Detection Using Wearable Sensors and Machine Learning
Abdel-Ghani, A., Abughazzah, Z., Akhund, M., Abualsaud, K., & Yaacoub, E. E. (2023) · International Wireless Communications and Mobile Computing Conference (IWCMC) · doi:10.1109/iwcmc58020.2023.10182781 · Cited by 6
“Recent efforts have demonstrated that the coughing sound can identify whether a suspected patient is infected with COVID-19 or not [12-15].”
BackgroundHoang, V. T., Nguyen, Q., Nguyen, Q. C., Nguyen, X. P., & Nguyen, H. (2023) · PHM Society Asia-Pacific Conference · doi:10.36001/phmap.2023.v4i1.3604 · Cited by 6
“To detect COVID-19, there are also two well-known datasets from New York ( NYU Breathing Sounds for COVID-19 , 2020) and Cambridge (Brown et al., 2020) universities.”
Dar, J. A., Srivastava, K. K., & Lone, S. A. (2022) · International Journal of Intelligent Computing and Cybernetics · doi:10.1108/ijicc-03-2022-0062 · Cited by 6
SRC: Superior Robustness of COVID-19 Detection from Noisy Cough Data Using GFCC
Swain, B. K., Khan, M. Z., Chowdhary, C. L., & Alsaeedi, A. (2023) · Computer Systems Science and Engineering · doi:10.32604/csse.2023.036192 · Cited by 6
Automatic COVID-19 detection using machine learning and voice recording
Benmalek, E., Mhamdi, J. E., Jilbab, A., & Jbari, A. (2023) · Research on Biomedical Engineering · doi:10.1007/s42600-023-00291-x · Cited by 6
Developing a multi-variate prediction model for COVID-19 from crowd-sourced respiratory voice data
Yan, Y., Aljbawi, W., Simons, S. O., & Urovi, V. (2024) · Exploration of Digital Health Technologies · doi:10.37349/edht.2024.00022 · Cited by 6
“HuBERT model is an end-to-end model, the CNN encoder in HuBERT is composed of seven 512-channel layers with strides [5,2,2,2,2,2,2] and kernel widths [10,3,3,3,3,2,2].”
BackgroundMethodInfluentialImpact of face coverings on cough measurement characterization
Cohen-McFarlane, M., Xi, P., Wallace, B., Valdés, J. J., Goubran, R. A., & Knoefel, F. D. (2021) · IEEE International Symposium on Medical Measurements and Applications (MeMeA) · doi:10.1109/memea52024.2021.9478728 · Cited by 6
Detecting COVID-19 from respiratory sound recordings with transformers
Aytekin, I., Dalmaz, O., Ankışhan, H., Sarıtaş, E. Ü., Bağcı, U., Çukur, T., & Celik, H. (2022) · SPIE Medical Imaging: Computer-Aided Diagnosis · doi:10.1117/12.2611490 · Cited by 6
“, MFCC, spectrogram) and data-driven (VGG-based) features were taken as inputs as described in.(8) An SVM classifier was then built for each task to detect COVID patients.”
BackgroundMethodInfluentialClassification of Respiratory Diseases and COVID-19 from Respiratory and Cough Sounds
Ahasan, M. M., Fahim, M. S. H., Mazumder, H., Fatema, N. E., Rahman, S. M., Islam, A. B. M. A. A., & Noor, J. (2022) · International Conference on Innovation and Intelligence for Informatics, Computing, and Technologies (3ICT) · doi:10.1109/3ict56508.2022.9990866 · Cited by 6
“Likewise, study [7] presented a COVID-19 diagnosis model using machine learning classifiers with coughs and breathing sound data.”
MethodCough Classification with Deep Derived Features using Audio Spectrogram Transformer
Valdés, J. J., Habashy, K., Xi, P., Cohen-McFarlane, M., Wallace, B., Goubran, R. A., & Knoefel, F. D. (2022) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata55660.2022.10020878 · Cited by 6
“In [8], handcrafted features such as RMS energy of STFT, spectral centroid, roll-off frequency, and more were concatenated in a feature vector and fed into a shallow network, reaching a precision score of 80% in Covid-19 cough diagnosis.”
MethodHan, J., Montagna, M., Grammenos, A., Xia, T., Bondareva, E., Brown, C., Chauhan, J., Dang, T., Spathis, D., Floto, R. A., et al. (2023) · Journal of Medical Internet Research · doi:10.2196/44804 · Cited by 6
“In our previous study, audio data collection and research on audio-based COVID-19 prediction was performed [26,27].”
Self-citationAcoustery System for Differential Diagnosing of Coronavirus COVID-19 Disease
Mitrofanova, A., Mikhaylov, D., Shaznaev, I., Chumanskaia, V., & Saveliev, V. (2021) · IEEE Open Journal of Engineering in Medicine and Biology · doi:10.1109/ojemb.2021.3127078 · Cited by 6
“The works [6], [8], [12] use preliminary data processing aimed at extracting the frequency parameters of cough recording.”
BackgroundMethodInfluentialPiecewise Position Encoding in Convolutional Neural Network for Cough-Based Covid-19 Detection
Shen, J., Zhang, X., Zhang, P., Yan, Y., Zhang, S., Huang, Z., Tang, Y., Wang, Y., Zhang, F., & Sun, A. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10095316 · Cited by 8
“These studies mainly used handcrafted features and machine learning methods for classification [3, 4].”
MethodA cough-based Covid-19 detection with gammatone and mel-frequency cepstral coefficients
Benmalek, E., Mhamdi, J. E., Jilbab, A., & Jbari, A. (2023) · Diagnostyka · doi:10.29354/diag/166330 · Cited by 6
“Recent studies have been examining the differences between respiratory sounds from healthy persons and patients who tested positive for COVID19 (such as coughs, breathing, and voice) [12-13], an electronic stethoscope was used to capture and evaluate the respiratory sounds of ten individuals who had COVID-19 infection…”
BackgroundMobile Sensing in the COVID-19 Era: A Review
Wang, Z., Xiong, H., Tang, M., Boukhechba, M., Flickinger, T., & Barnes, L. E. (2022) · Health Data Science · doi:10.34133/2022/9830476 · Cited by 7
Hidden Follower Detection: How Is the Gaze-Spacing Pattern Embodied in Frequency Domain?
Li, S., Hu, R., Li, S., & Liao, L. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i1.27809 · Cited by 6
“…the universality of frequency-domain features for hidden following behavior, we choose a classical feature and a complex feature: Mel-Frequency Cepstral Coefficient (MFCC) (Murty and Yegnanarayana 2006; Brown et al. 2020): MFCC is the most common and representative feature (Lee et al. 2019).”
BackgroundDvoynikova, A., Markitantov, M., Рюмина, Е. В., Ryumin, D., & Karpov, A. A. (2021) · Informatics and Automation · doi:10.15622/20.5.5 · Cited by 6
A Scalable and Domain Adaptive Respiratory Symptoms Detection Framework using Earables
Nguyen, N. T. V., Chakma, A., & Roy, N. (2021) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata52589.2021.9671796 · Cited by 5
“Statistical features similar to [17] are extracted for the traditional machine learning models using the python-based library - tsfresh [18].”
MethodDenoising Cough Sound Recordings Using Neural Networks
Jose, L., Berkovsky, S., Xiong, H., Mascolo, C., & Sharan, R. V. (2023) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc40787.2023.10340687 · Cited by 5
“There is also the possibility of using cough sound analysis as a screening tool for COVID-19 [4].”
BackgroundMethodSelf-citationIoT-Based Framework for COVID-19 Detection Using Machine Learning Techniques
Al-Khaleefa, A. S., Musawi, G. F. K. A., & Saeed, T. J. (2023) · Sci · doi:10.3390/sci6010002 · Cited by 5
“The study in [32], has been presented as a system of COVID-19 detection.”
MethodA New Smartphone-Based Method for Remote Health Monitoring: Assessment of Respiratory Kinematics
Vignali, E., Gasparotti, E., Miglior, L., Gervasi, V., Simone, L., Haxhiademi, D., Frediani, L., Borelli, G., Berti, S. L., & Celi, S. (2024) · Electronics · doi:10.3390/electronics13061132 · Cited by 5
Multimodal Detection of COVID-19 Symptoms using Deep Learning & Probability-based Weighting of Modes
Effati, M., Sun, Y.-C., Naguib, H. E., & Nejat, G. (2021) · IEEE International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob) · doi:10.1109/wimob52687.2021.9606355 · Cited by 5
Detection of Covid-19 through Cough and Breathing Sounds using CNN
Evangeline, D., Lohit, S. M., Tarun, R., Ujwal, K. C., & Sai Viswa Sumanth, D. (2021) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2021.0121218 · Cited by 6
“The authors in [12] have proposed detection of Covid-19 using cough and breathing sounds.”
BackgroundAutomated Covid-19 Respiratory Symptoms Analysis from Speech and Cough
Pleva, M., Martens, E., & Juhár, J. (2022) · IEEE World Symposium on Applied Machine Intelligence and Informatics (SAMI) · doi:10.1109/sami54271.2022.9780815 · Cited by 5
Multi-Type Outer Product-Based Fusion of Respiratory Sounds for Detecting COVID-19
Mallol-Ragolta, A., Cuesta, H., Gómez, E., & Schuller, B. W. (2022) · Interspeech (USB) · doi:10.21437/interspeech.2022-10291 · Cited by 5
“In this regard, researchers have exploited cough [8, 9, 10], breath [11, 12], and speech [13, 14] information for this task.”
BackgroundOmiya, Y., Mizuguchi, D., & Tokuno, S. (2023) · International Journal of Environmental Research and Public Health · doi:10.3390/ijerph20043415 · Cited by 5
TinyM$^2$Net: A Flexible System Algorithm Co-designed Multimodal Learning Framework for Tiny DevicesPreprint
Rashid, H.-A., Ovi, P. R., Busart, C., Gangopadhyay, A., & Mohsenin, T. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2202.04303 · Cited by 8
“This dataset is a subset of the bigger dataset [8] collected by University of Cambridge.”
BackgroundMethodZimmer, A., Ravi, V., Espinoza‐Lopez, P., Kafentzis, G. P., Ravanelli, M., Rahimi, S. A., Pai, M., Ugarte‐Gil, C., & Lapierre, S. G. (2026) · Annals of Epidemiology · doi:10.1016/j.annepidem.2026.110076 · Cited by 4
Automatic COVID-19 Detection from Cough Sounds Using Multi-Headed Convolutional Neural Networks
Wang, W., Shang, Q., & Lu, H. (2023) · Applied Sciences · doi:10.3390/app13126976 · Cited by 7
“The first is to distinguish COVID-positive from non-COVID samples, the second is to distinguish COVID-positive with a cough from non-COVID with a cough, and the third is to distinguish COVID-positive coughs from non-COVID asthma coughs [20].”
BackgroundA Resource Efficient System for On-Smartwatch Audio Processing
Ahmed, M. S., Rahman, A., Wang, Z., Rucker, M., & Barnes, L. E. (2024) · ACM Annual International Conference on Mobile Computing and Networking (MobiCom) · doi:10.1145/3636534.3698866 · Cited by 4
“Recently, audio processing has received much attention in real-time applications for problems such as pulmonary patient [3], breathing phase [22], breathing exercises [17], cough [11] and COVID-19 [6] detection.”
Alshurideh, M. T., Khatib, M. M. E., Al-Sulaiti, K., Sukkari, L. S., Kurdi, B. H. A., Nawaiseh, A. K., Alrawabdeh, W. A., Alshurideh, A., Shwedeh, F., & Alzoubi, H. M. (2025) · Advances in Science, Technology & Innovation/Advances in science, technology & innovation · doi:10.1007/978-3-031-90131-7_6 · Cited by 4
Buttar, H. M., Rahman, M. M. U., Nawaz, M. W., Mian, A. N., Zahid, A., & Abbasi, Q. H. (2026) · Communications Medicine · doi:10.1038/s43856-025-01181-2 · Cited by 4
“This hasmotivatedtheresearcherstodesignacollectionofmethodsthatutilize oneofthefollowingmodalitiestodiagnoseCOVID-19andotherlung diseases:thelungsounds(throughauscultation),speechsignals,breathing sounds,andcoughsounds 20,21 .”
Coughing-Based Recognition of Covid-19 with Spatial Attentive ConvLSTM Recurrent Neural Networks
Yan, T., Meng, H., Parada‐Cabaleiro, E., Liu, S., Song, M., & Schuller, B. W. (2021) · Interspeech (USB) · doi:10.21437/interspeech.2021-630 · Cited by 5
“For our experiments, a subset of the Cambridge COVID-19 Sound database [34], as used in the COVID-19 Cough SubChallenge (CCS) from the INTERSPEECH 2021 Computational Paralinguistics ChallengE (ComParE) [12], is considered.”
MethodLong Short-Term Memory-based Deep Learning Model for COVID-19 Detection using Coughing Sound
Malviya, A., Dixit, R., Shukla, A., & Kushwaha, N. (2023) · SN Computer Science · doi:10.1007/s42979-023-01934-7 · Cited by 4
“Hence coughing, and other respiratory data like breathing and sneezing, are used to detect and diagnose respiratory illness via machine learning algorithms [16–18].”
MethodPoberezhets, V., Kasteleyn, M. J., & Aardoom, J. J. (2023) · European Respiratory Society eBooks · doi:10.1183/2312508x.10001623 · Cited by 5
Spectral–temporal saliency masks and modulation tensorgrams for generalizable COVID-19 detection
Zhu, Y. M., & Falk, T. H. (2024) · Computer Speech & Language · doi:10.1016/j.csl.2024.101620 · Cited by 5
Kumar, M. R. D., Paval, K. S., Sanghamitra, S., Surya, N. T. S., Lal, G. J., & Ravi, V. (2024) · Lecture notes in networks and systems · doi:10.1007/978-981-99-9043-6_8 · Cited by 4
Rahman, T., Hossain, F., Tonmoy, T. H., Nuvvula, S., Chapman, B. P., Gupta, R., Lover, A., Dinglasan, R., & Stephanie, C. (2024) · Frontiers in Public Health · doi:10.3389/fpubh.2024.1279392 · Cited by 4
Pigoli, D., Baker, K., Budd, J., Butler, L., Coppock, H., Egglestone, S., Gilmour, S. G., Holmes, C. C., Hurley, D., Jersakova, R., et al. (2024) · Statistics in Medicine · doi:10.1002/sim.10211 · Cited by 4
Mostaani, Z., Prasad, R., Vlasenko, B., & Magimai.-Doss, M. (2022) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp43922.2022.9746271 · Cited by 4
“Similar efforts are taking place in the research community [3, 4, 5].”
ResultAn explainable COVID-19 detection system based on human sounds
Li, H., Chen, X., Qian, X., Chen, H., Li, Z., Bhattacharjee, S., Zhang, H., Huang, M.-C., & Xu, W. (2022) · Smart Health · doi:10.1016/j.smhl.2022.100332 · Cited by 4
“Baseline To objectively evaluate our system performance, we construct a baseline that applies a state-of-the-art respiratory sound-based OVID detection model (Brown et al., 2020) on our dataset.”
InfluentialKnowledge Transfer and Crowdsourcing in Cyber-Physical-Social Systems
Kumar, G., Narducci, F., & Bakshi, S. (2022) · Pattern Recognition Letters · doi:10.1016/j.patrec.2022.10.027 · Cited by 4
Efficient covid19 disease diagnosis based on cough signal processing and supervised machine learning
Bensid, K., Lati, A., Benlamoudi, A., Ghouar, B., & Senoussi, M. L. (2022) · Diagnostyka · doi:10.29354/diag/156751 · Cited by 4
“In [5], "C. Brown" presented his proposed system for detecting asthma and COVID together, where his study was based on a large-scale crowdsourced dataset of respiratory sounds.”
BackgroundContinuous Monitoring for Diagnosis: A Wearable for Covid-19 Detection in Symptomatic Patients
Mila, S. A., Kabir, M. R., & Ray, S. (2023) · International Conference on Consumer Electronics · doi:10.1109/icce56470.2023.10043456 · Cited by 4
“There has also been work on a variety of ML models for predicting infection from a variety of symptoms such as cough and breathing data [7], [8]. n another work, Das et al. have proposed an ensembled learning model based on conventional deep convolutional neural networks to detect COVID infection…”
BackgroundFischer, A., Aguayo, G., Oustric, P., Morin, L., Larche, J., Benoy, C., & Fagherazzi, G. (2023) · JMIR Research Protocols · doi:10.2196/46103 · Cited by 4
“For example, voice features have previously been associated with a COVID-19 infection or a consequence of COVID-19 infection [15,16].”
Covid Cough Identification using Machine Learning and Deep Learning Networks
Vinod, A., Mohan, N., Kumar, S. S., & Soman, K. P. (2023) · International Conference on Intelligent Technologies (CONIT) · doi:10.1109/conit59222.2023.10205895 · Cited by 4
“The work presented in [11] explains data processing on a big crowd sourcing data of respiratory sounds to help with diagnosis procedure.”
BackgroundCovidEnvelope: A Fast Automated Approach to Diagnose COVID-19 from Cough SignalsPreprint
Hossain, M. Z., Uddin, M. B., & Ahmed, K. A. (2021) · medRxiv · doi:10.1101/2021.04.16.21255630 · Cited by 4
“[4] used large-scale crowdsourced dataset of respiratory sounds and extracted various features before detecting COVID-19 cough using logistic regression, gradient boosting trees (GBT) and support vector machines (SVM).”
BackgroundMethod
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.