{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T06:46:42Z","timestamp":1782283602489,"version":"3.54.5"},"reference-count":35,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T00:00:00Z","timestamp":1782259200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100006762","name":"Atlantic Research Center for Information and Communication Technologies","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100006762","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Med."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Voice analysis has emerged as a promising non-invasive approach for monitoring respiratory and systemic health conditions. However, subtle physiological alterations are often difficult to capture using recordings collected at rest. In addition, combining traditional acoustic descriptors with modern self-supervised speech representations may provide complementary information for clinical voice analysis.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>This study evaluates a generalized screening model integrating stress-induced acoustic analysis with machine learning. We investigate how physical exertion and the fusion of traditional acoustic features with self-supervised learning embeddings (such as wav2vec 2.0 and WavLM) enhance the diagnostic sensitivity of vocal and respiratory signals. Post-Acute Sequelae of SARS-CoV-2 (PASC) is used as a case study to evaluate the proposed framework.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      Utilizing the DICOPERIA-Voice dataset (\n                      <jats:italic>n<\/jats:italic>\n                      = 154), we collected recordings of sustained vowel phonation (\/a\/) and voluntary coughing at two clinical moments: resting state and following a physiological stress protocol (six-minute walk and one-minute sit-to-stand tests). We employed a dual-feature extraction strategy, combining traditional acoustic biomarkers with high-dimensional Self-Supervised Learning (SSL) embeddings from wav2vec 2.0, WavLM and HuBERT. Binary classification (PASC vs. Healthy) was performed using Logistic Regression, evaluated via stratified 5-fold cross-validation.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Physical exertion significantly improved classification performance and reduced model variability across all tasks. The fusion of acoustic features, WavLM and wav2vec 2.0 achieved peak F1-scores of 82.2% for vowel phonation and 80.8% for coughing both in post-exercise conditions. A cross-task late fusion model aggregation reached the highest overall performance, with an F1-score of 87.7%.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Incorporating Self-Supervised Learning representations into acoustic analysis improves the sensitivity of voice-based screening, while post-exercise measurements further enhance the robustness and consistency of classification. Together, these strategies provide a scalable and objective framework for detecting respiratory and vocal sequelae in chronic or post-viral conditions. With further validation, this approach could be integrated into routine functional assessments, offering a rapid, non-invasive adjunct to clinical decision-making.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fmed.2026.1864436","type":"journal-article","created":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T05:47:58Z","timestamp":1782280078000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Improving respiratory disease detection through SSL-enhanced acoustic analysis and exercise-rest measurements"],"prefix":"10.3389","volume":"13","author":[{"given":"\u00c1lvaro","family":"Vera-L\u00f3pez","sequence":"first","affiliation":[{"name":"Multimedia Technologies Group (GTM)","place":["atlanTTic Research Center, Universidade de Vigo, Spain"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dar\u00edo","family":"Tilves-Santiago","sequence":"additional","affiliation":[{"name":"Multimedia Technologies Group (GTM)","place":["atlanTTic Research Center, Universidade de Vigo, Spain"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jos\u00e9 Manuel","family":"Ram\u00edrez-S\u00e1nchez","sequence":"additional","affiliation":[{"name":"Multimedia Technologies Group (GTM)","place":["atlanTTic Research Center, Universidade de Vigo, Spain"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Laura","family":"Doc\u00edo-Fern\u00e1ndez","sequence":"additional","affiliation":[{"name":"Multimedia Technologies Group (GTM)","place":["atlanTTic Research Center, Universidade de Vigo, Spain"]},{"name":"Multimedia Technologies Group (GTM)","place":["Galicia Sur Health Research Institute (IIS Galicia Sur), Vigo, Spain"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Carmen","family":"Garc\u00eda-Mateo","sequence":"additional","affiliation":[{"name":"Multimedia Technologies Group (GTM)","place":["atlanTTic Research Center, Universidade de Vigo, Spain"]},{"name":"Multimedia Technologies Group (GTM)","place":["Galicia Sur Health Research Institute (IIS Galicia Sur), Vigo, Spain"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mar\u00eda","family":"Bustillo-Casado","sequence":"additional","affiliation":[{"name":"Department of Internal Medicine","place":["Complexo Hospitalario Universitario de Ourense, SERGAS, Spain"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alejandro","family":"Garc\u00eda-Caballero","sequence":"additional","affiliation":[{"name":"Department of Psychiatry","place":["Complexo Hospitalario Universitario de Ourense, SERGAS, Spain"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,6,24]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"585","DOI":"10.1016\/S2213-2600(20)30105-03","article-title":"Prevalence and attributable health burden of chronic respiratory diseases, 1990\u20132017: a systematic analysis for the Global Burden of Disease Study","volume":"8","author":"Soriano","year":"2020","journal-title":"Lancet Respiratory Med"},{"key":"B2","doi-asserted-by":"publisher","first-page":"789","DOI":"10.1016\/j.amjmed.2008.04.030","article-title":"COPD as a systemic disease: impact on physical functional limitations","volume":"121","author":"Eisner","year":"2008","journal-title":"Am J Med"},{"key":"B3","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1044\/persp1.SIG3.94","article-title":"The relationship between voice and breathing in the assessment and treatment of voice disorders","volume":"1","author":"Lewandowski","year":"2016","journal-title":"Perspect ASHA Spec Interest Groups"},{"key":"B4","doi-asserted-by":"publisher","first-page":"761","DOI":"10.1016\/j.jvoice.2015.09.017","article-title":"Voice disorders: etiology and diagnosis","volume":"30","author":"Martins","year":"2016","journal-title":"J Voice"},{"key":"B5","doi-asserted-by":"publisher","first-page":"S1","DOI":"10.1177\/0194599817751030","article-title":"Clinical practice guideline: hoarseness (dysphonia) (update)","volume":"158","author":"Stachler","year":"2018","journal-title":"Otolaryngol-Head Neck Surg"},{"key":"B6","doi-asserted-by":"publisher","first-page":"301","DOI":"10.52533\/JOHS.2022.21005","article-title":"Etiologies, Evaluation, and differential diagnosis of dysphonia","volume":"2","author":"Abduljabbar","year":"2022","journal-title":"J Healthcare Sci"},{"key":"B7","article-title":"Dysphonia","author":"Neighbors","year":"2024","journal-title":"StatPearls"},{"key":"B8","doi-asserted-by":"publisher","first-page":"1390","DOI":"10.1044\/2024_AJSLP-23-00175","article-title":"Language-independent acoustic biomarkers for quantifying speech impairment in Huntington's disease","volume":"33","author":"Fahed","year":"2024","journal-title":"Am J Speech-Lang Pathol"},{"key":"B9","doi-asserted-by":"publisher","first-page":"947","DOI":"10.1016\/j.jvoice.2018.07.014","article-title":"A survey on machine learning approaches for automatic detection of voice disorders","volume":"33","author":"Hegde","year":"2019","journal-title":"J Voice"},{"key":"B10","doi-asserted-by":"publisher","first-page":"220","DOI":"10.3389\/fnagi.2019.00220","article-title":"Deep learning in Alzheimer's disease: diagnostic classification and prognostic prediction using neuroimaging data","volume":"11","author":"Jo","year":"2019","journal-title":"Front Aging Neurosci"},{"key":"B11","unstructured":"Post COVID-19 condition (long COVID)\n          \n          2025"},{"key":"B12","doi-asserted-by":"publisher","first-page":"601","DOI":"10.1038\/s41591-021-01283-z","article-title":"Post-acute COVID-19 syndrome","volume":"27","author":"Nalbandian","year":"2021","journal-title":"Nat Med"},{"key":"B13","doi-asserted-by":"publisher","first-page":"103950","DOI":"10.1016\/j.amjoto.2023.103950","article-title":"COVID-related dysphonia and persistent long-COVID voice sequelae: a systematic review and meta-analysis","volume":"44","author":"Lin","year":"2023","journal-title":"Am J Otolaryngol"},{"key":"B14","doi-asserted-by":"publisher","first-page":"288","DOI":"10.1159\/000361047","article-title":"The effect of physical effort on voice characteristics","volume":"65","author":"Primov-Fever","year":"2013","journal-title":"Folia Phoniatrica et Logopaedica"},{"key":"B15","doi-asserted-by":"publisher","first-page":"n1648","DOI":"10.1136\/bmj.n1648","article-title":"Long covid-mechanisms, risk factors, and management","volume":"374","author":"Crook","year":"2021","journal-title":"BMJ"},{"key":"B16","doi-asserted-by":"publisher","first-page":"5093","DOI":"10.3390\/ijerph19095093","article-title":"The relationship between physical activity and long COVID: a cross-sectional study","volume":"19","author":"Wright","year":"2022","journal-title":"Int J Environ Res Public Health"},{"key":"B17","doi-asserted-by":"publisher","first-page":"855","DOI":"10.1515\/jisys-2022-0058","article-title":"review on voice pathology: Taxonomy, diagnosis, medical procedures and detection techniques, open challenges, limitations, and recommendations for future directions","volume":"31","author":"Abdulmajeed","year":"2022","journal-title":"J Intellig Syst"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2006.11477","article-title":"wav2vec 2","author":"Baevski","year":"2006","journal-title":"arXiv"},{"key":"B19","doi-asserted-by":"publisher","first-page":"1505","DOI":"10.1109\/JSTSP.2022.3188113","article-title":"WavLM: large-scale self-supervised pre-training for full stack speech processing","volume":"16","author":"Chen","year":"2022","journal-title":"IEEE J Sel Top Signal Process"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291","article-title":"HuBERT: self-supervised speech representation learning by masked prediction of hidden units","author":"Hsu","year":"2021","journal-title":"arXiv"},{"key":"B21","doi-asserted-by":"publisher","first-page":"14915","DOI":"10.1109\/ACCESS.2023.3243986","article-title":"Automatic voice disorder detection using self-supervised representations","volume":"11","author":"Ribas","year":"2023","journal-title":"IEEE Access"},{"key":"B22","unstructured":"COPERIA\n              Project\n            \n          \n          \n          2022"},{"key":"B23","doi-asserted-by":"publisher","first-page":"783","DOI":"10.4187\/respcare.03480783","article-title":"The six-minute walk test","volume":"48","author":"Enright","year":"2003","journal-title":"Respir Care"},{"key":"B24","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1097\/HCR.0000000000000336","article-title":"1-minute sit-to-stand test: systematic review of procedures, performance, and clinimetric properties","volume":"39","author":"Bohannon","year":"2019","journal-title":"J Cardiopulm Rehabil Prev"},{"key":"B25","doi-asserted-by":"crossref","first-page":"2001","DOI":"10.21437\/Interspeech.2016-129","article-title":"The INTERSPEECH 2016 computational paralinguistics challenge: deception, sincerity & native language","volume-title":"Interspeech","author":"Schuller","year":"2016"},{"key":"B26","first-page":"1405","volume-title":"Exploiting Foundation Models and Speech Enhancement for Parkinson's Disease Detection from Speech in Real-World Operative Conditions","author":"La Quatra","year":"2024"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2111.09296","article-title":"XLS-R: self-supervised cross-lingual speech representation learning at scale","author":"Babu","year":"2021","journal-title":"arXiv"},{"key":"B28","doi-asserted-by":"publisher","first-page":"728","DOI":"10.3390\/bioengineering12070728","article-title":"Speech-based Parkinson's detection using pre-trained self-supervised automatic speech recognition (ASR) models and supervised contrastive learning","volume":"12","author":"Sedigh Malekroodi","year":"2025","journal-title":"Bioengineering"},{"key":"B29","first-page":"1003","volume-title":"Effect of Physical Exercise on Voice in People Living with COPD","author":"Reinders","year":"2025"},{"key":"B30","doi-asserted-by":"publisher","first-page":"2015","DOI":"10.1186\/s13636-015-0072-7","article-title":"Physical task stress and speaker variability in voice quality","volume":"10","author":"Godin","year":"2015","journal-title":"EURASIP J Audio, Speech, Music Proc"},{"key":"B31","doi-asserted-by":"publisher","first-page":"1467","DOI":"10.1007\/s00455-023-10574-1","article-title":"Acoustic analysis of voluntary coughs, throat clearings, and induced reflexive coughs in a healthy population","volume":"38","author":"Mootassim-Billah","year":"2023","journal-title":"Dysphagia"},{"key":"B32","doi-asserted-by":"publisher","first-page":"383","DOI":"10.1007\/s00455-015-9687-1","article-title":"Voluntary cough airflow differentiates safe versus unsafe swallowing in amyotrophic lateral sclerosis","volume":"31","author":"Plowman","year":"2016","journal-title":"Dysphagia"},{"key":"B33","doi-asserted-by":"publisher","first-page":"8303","DOI":"10.3390\/jcm14238303","article-title":"Validity and reliability of the six-minute walking test compared to cardiopulmonary exercise test in individuals with heart failure systematic review and meta-analysis","volume":"14","author":"Pepera","year":"2025","journal-title":"J Clini Med"},{"key":"B34","doi-asserted-by":"publisher","first-page":"248","DOI":"10.3390\/electronics14020248","article-title":"Deep audio features and self-supervised learning for early diagnosis of neonatal diseases: sepsis and respiratory distress syndrome classification from infant cry signals","volume":"14","author":"Shayegh","year":"2025","journal-title":"Electronics"},{"key":"B35","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1371\/journal.pdig.0001076","article-title":"Speaker-independent dysarthria severity classification using self-supervised transformers and multi-task learning","volume":"4","author":"Kadirvelu","year":"2025","journal-title":"PLoS Digital Health"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1864436\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T05:48:03Z","timestamp":1782280083000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1864436\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,24]]},"references-count":35,"alternative-id":["10.3389\/fmed.2026.1864436"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2026.1864436","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,24]]},"article-number":"1864436"}}