{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T21:27:14Z","timestamp":1783632434841,"version":"3.55.0"},"reference-count":45,"publisher":"Elsevier BV","issue":"4","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"}],"funder":[{"DOI":"10.13039\/100010665","name":"H2020 Marie Sk\u0142odowska-Curie Actions","doi-asserted-by":"publisher","award":["101007666"],"award-info":[{"award-number":["101007666"]}],"id":[{"id":"10.13039\/100010665","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010067","name":"Gobierno de Arag\u00f3n","doi-asserted-by":"publisher","award":["T36 23R"],"award-info":[{"award-number":["T36 23R"]}],"id":[{"id":"10.13039\/501100010067","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010661","name":"Horizon 2020 Framework Programme","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100010661","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002923","name":"Consejo Nacional de Investigaciones Cient\u00edficas y T\u00e9cnicas","doi-asserted-by":"publisher","award":["PIP2021-2023-11220200101038"],"award-info":[{"award-number":["PIP2021-2023-11220200101038"]}],"id":[{"id":"10.13039\/501100002923","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["clinicalkey.com","clinicalkey.com.au","clinicalkey.es","clinicalkey.fr","clinicalkey.jp","jvoice.org","elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Voice"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.jvoice.2024.03.001","type":"journal-article","created":{"date-parts":[[2024,5,28]],"date-time":"2024-05-28T23:34:03Z","timestamp":1716939243000},"page":"974-986","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":4,"title":["Automatic Voice Disorder Detection from a Practical Perspective"],"prefix":"10.1016","volume":"40","author":[{"given":"Jazmin","family":"Vidal","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dayana","family":"Ribas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cyntia","family":"Bonomi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eduardo","family":"Lleida","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9137-4013","authenticated-orcid":false,"given":"Luciana","family":"Ferrer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alfonso","family":"Ortega","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.jvoice.2024.03.001_bib1","doi-asserted-by":"crossref","first-page":"281","DOI":"10.1044\/1092-4388(2004\/023)","article-title":"Prevalence of voice disorders in teachers and the general population","volume":"47","author":"Roy","year":"2004","journal-title":"J Speech Lang Hear Res"},{"key":"10.1016\/j.jvoice.2024.03.001_bib2","doi-asserted-by":"crossref","first-page":"1988","DOI":"10.1097\/01.mlg.0000179174.32345.41","article-title":"Voice disorders in the general population: prevalence, risk factors, and occupational impact","volume":"115","author":"Roy","year":"2005","journal-title":"Laryngoscope"},{"key":"10.1016\/j.jvoice.2024.03.001_bib3","doi-asserted-by":"crossref","first-page":"2359","DOI":"10.1002\/lary.24740","article-title":"The prevalence of voice problems among adults in the United States","volume":"124","author":"Bhattacharyya","year":"2014","journal-title":"Laryngoscope"},{"key":"10.1016\/j.jvoice.2024.03.001_bib4","doi-asserted-by":"crossref","first-page":"386.e1","DOI":"10.1016\/j.jvoice.2016.09.009","article-title":"Intra- and inter-database study for Arabic, English, and German databases: do conventional speech features detect voice pathology?","volume":"31","author":"Ali","year":"2017","journal-title":"J Voice"},{"key":"10.1016\/j.jvoice.2024.03.001_bib5","doi-asserted-by":"crossref","first-page":"124048","DOI":"10.1109\/ACCESS.2019.2938265","article-title":"Leveraging artificial intelligence to improve voice disorder identification through the use of a reliable mobile app","volume":"7","author":"Verde","year":"2019","journal-title":"IEEE Access"},{"key":"10.1016\/j.jvoice.2024.03.001_bib6","series-title":"Advances in Speech and Language Technologies for Iberian Languages - IberSPEECH 2012 Conference, Madrid, Spain, November 21\u201323, 2012. Proceedings, Volume 328 of Communications in Computer and Information Science","first-page":"99","article-title":"Voice pathology detection on the saarbr\u00fccken voice database with calibration and fusion of scores using multifocal toolkit","author":"Gonz\u00e1lez","year":"2012"},{"key":"10.1016\/j.jvoice.2024.03.001_bib7","doi-asserted-by":"crossref","unstructured":"H. Wu, J. Soraghan, A. Lowit, et al. A deep learning method for pathological voice detection using convolutional deep belief network. Proceedings of Interspeech 2018. ISCA, 2018:446\u2013450.","DOI":"10.21437\/Interspeech.2018-1351"},{"key":"10.1016\/j.jvoice.2024.03.001_bib8","unstructured":"Y.-T. Hsu, Z. Zhu, C.-T. Wang,\u00a0et al. Robustness against the channel effect in pathological voice detection. ArXiv, abs\/1811.10376, 2018."},{"key":"10.1016\/j.jvoice.2024.03.001_bib9","doi-asserted-by":"crossref","unstructured":"P. Har\u00e1r, J. Alonso, J. Mekyska, et al. Voice pathology detection using deep learning: a preliminary study; 2017:1\u20134.","DOI":"10.1109\/IWOBI.2017.7985525"},{"key":"10.1016\/j.jvoice.2024.03.001_bib10","doi-asserted-by":"crossref","first-page":"41034","DOI":"10.1109\/ACCESS.2018.2856238","article-title":"Voice pathology detection using deep learning on mobile healthcare framework","volume":"6","author":"Alhussein","year":"2018","journal-title":"IEEE Access"},{"key":"10.1016\/j.jvoice.2024.03.001_bib11","doi-asserted-by":"crossref","DOI":"10.3390\/app10113723","article-title":"Voice pathology detection and classification using convolutional neural network model","volume":"10","author":"Mohammed","year":"2020","journal-title":"Appl Sci"},{"key":"10.1016\/j.jvoice.2024.03.001_bib12","article-title":"A deep learning approach for voice disorder detection for smart connected living environments","volume":"22","author":"Verde","year":"2021","journal-title":"ACM Trans Internet Technol"},{"key":"10.1016\/j.jvoice.2024.03.001_bib13","doi-asserted-by":"crossref","DOI":"10.1016\/j.bspc.2019.101615","article-title":"Acoustic investigation of speech pathologies based on the discriminative paraconsistent machine (dpm)","volume":"55","author":"Fonseca","year":"2020","journal-title":"Biomed Signal Process Control"},{"key":"10.1016\/j.jvoice.2024.03.001_bib14","doi-asserted-by":"crossref","first-page":"5196","DOI":"10.3390\/s23115196","article-title":"An experimental analysis on multicepstral projection representation strategies for dysphonia detection","volume":"23","author":"Contreras","year":"2023","journal-title":"Sensors"},{"key":"10.1016\/j.jvoice.2024.03.001_bib15","doi-asserted-by":"crossref","first-page":"367","DOI":"10.1109\/JSTSP.2019.2957988","article-title":"Analysis and detection of pathological voice using glottal source features","volume":"14","author":"Kadiri","year":"2020","journal-title":"J Sel Top Signal Process"},{"key":"10.1016\/j.jvoice.2024.03.001_bib16","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1016\/j.neunet.2021.02.008","article-title":"Residual neural network precisely quantifies dysarthria severity-level based on short-duration speech segments","volume":"139","author":"Gupta","year":"2021","journal-title":"Neural Netw"},{"key":"10.1016\/j.jvoice.2024.03.001_bib17","doi-asserted-by":"crossref","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":"10.1016\/j.jvoice.2024.03.001_bib18","doi-asserted-by":"crossref","first-page":"947.e11","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":"10.1016\/j.jvoice.2024.03.001_bib19","unstructured":"M. P\u00fctzer and J. Koreman. A German database of pathological vocal fold vibration; 1997:143\u2013153."},{"key":"10.1016\/j.jvoice.2024.03.001_bib20","series-title":"Advances in Speech-language Pathology","article-title":"The Advanced Voice Function Assessment Databases (AVFAD): tools for voice clinicians and speech research, chapter 14","author":"Jesus","year":"2017"},{"key":"10.1016\/j.jvoice.2024.03.001_bib21","doi-asserted-by":"crossref","unstructured":"P. Barche, K. Gurugubelli, and A.K. Vuppala. Towards automatic assessment of voice disorders: a clinical approach. Proceedings of Interspeech 2018; 2020:2537\u20132541.","DOI":"10.21437\/Interspeech.2020-2160"},{"key":"10.1016\/j.jvoice.2024.03.001_bib22","doi-asserted-by":"crossref","unstructured":"M. Huckvale, C. Buciuleac. Automated detection of voice disorder in the Saarbr\u00fccken voice database: effects of pathology subset and audio materials. Interspeech; 2021:1399\u20131403.","DOI":"10.21437\/Interspeech.2021-1507"},{"key":"10.1016\/j.jvoice.2024.03.001_bib23","article-title":"Net benefit approaches to the evaluation of prediction models, molecular markers, and diagnostic tests","volume":"352","author":"Vickers","year":"2016","journal-title":"BMJ"},{"key":"10.1016\/j.jvoice.2024.03.001_bib24","doi-asserted-by":"crossref","unstructured":"P. Godau, P. Kalinowski, E. Christodoulou, et al. Deployment of image analysis algorithms under prevalence shifts. arxiv:2303.12540; 2023.","DOI":"10.1007\/978-3-031-43898-1_38"},{"key":"10.1016\/j.jvoice.2024.03.001_bib25","unstructured":"L. Maier-Hein, A. Reinke, P. Godau, et al. Metrics reloaded: Pitfalls and recommendations for image analysis validation. arxiv:2206.01653; 2022."},{"key":"10.1016\/j.jvoice.2024.03.001_bib26","unstructured":"L. Ferrer. Analysis and comparison of classification metrics. arXiv:2209.05355; 2022."},{"key":"10.1016\/j.jvoice.2024.03.001_bib27","doi-asserted-by":"crossref","DOI":"10.1016\/j.cmpb.2022.106930","article-title":"Decisions are not all equal\u2014introducing a utility metric based on case-wise raters\u2019 perceptions","volume":"221","author":"Campagner","year":"2022","journal-title":"Comput Methods Prog Biomed"},{"key":"10.1016\/j.jvoice.2024.03.001_bib28","series-title":"Pattern Recognition and Machine Learning, Volume 4 of Information Science and Statistics","author":"Bishop","year":"2006"},{"key":"10.1016\/j.jvoice.2024.03.001_bib29","doi-asserted-by":"crossref","first-page":"359","DOI":"10.1198\/016214506000001437","article-title":"Strictly proper scoring rules, prediction, and estimation","volume":"102","author":"Gneiting","year":"2012","journal-title":"J Am Stat Assoc"},{"key":"10.1016\/j.jvoice.2024.03.001_bib30","series-title":"Proceedings of the 34th International Conference on, Volume 70 of Proceedings of Research","first-page":"1321","article-title":"On calibration of modern neural networks","author":"Guo","year":"2017"},{"key":"10.1016\/j.jvoice.2024.03.001_bib31","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1016\/j.jclinepi.2015.12.005","article-title":"A calibration hierarchy for risk models was defined: from utopia to empirical data","volume":"74","author":"Van Calster","year":"2016","journal-title":"J Clin Epidemiol"},{"key":"10.1016\/j.jvoice.2024.03.001_bib32","article-title":"Validation of prediction models in the presence of competing risks: a guide through modern methods","volume":"377","author":"Van Geloven","year":"2022","journal-title":"BMJ"},{"key":"10.1016\/j.jvoice.2024.03.001_bib33","unstructured":"C. Mosquera, L. Ferrer, D. Milone, et al. Impact of class imbalance on chest x-ray classifiers: towards better evaluation practices for discrimination and calibration performance. arXiv preprint arXiv:2112.12843; 2021."},{"key":"10.1016\/j.jvoice.2024.03.001_bib34","unstructured":"M.P. Naeini, G. Cooper, and M. Hauskrecht. Obtaining well calibrated probabilities using bayesian binning. Twenty-Ninth AAAI Conference on Artificial Intelligence; 2015."},{"key":"10.1016\/j.jvoice.2024.03.001_bib35","doi-asserted-by":"crossref","unstructured":"T. Popordanoska, R. Sayer, and M.B. Blaschko. A consistent and differentiable Lp canonical calibration error estimator. Proceedings of NeurIPS, New Orleans; 2022.","DOI":"10.52202\/068431-0576"},{"key":"10.1016\/j.jvoice.2024.03.001_bib36","unstructured":"J. Nixon, M.W. Dusenberry, L. Zhang, et al. Measuring calibration in deep learning. CVPR Workshops; 2019."},{"key":"10.1016\/j.jvoice.2024.03.001_bib37","unstructured":"N. Br\u00fcmmer. Measuring, refining and calibrating speaker and language information extracted from speech. University of Stellenbosch, Stellenbosch; 2010."},{"key":"10.1016\/j.jvoice.2024.03.001_bib38","doi-asserted-by":"crossref","unstructured":"Hsu W, Bolte B, Tsai Y-HH, et al. HuBERT: self-supervised speech representation learning by masked prediction of hidden units. CoRR, abs\/2106.07447; 2021.","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"10.1016\/j.jvoice.2024.03.001_bib39","doi-asserted-by":"crossref","first-page":"9062","DOI":"10.3390\/app13169062","article-title":"Cross-corpus training strategy for speech emotion recognition using self-supervised representations","volume":"13","author":"Pastor","year":"2023","journal-title":"Appl Sci"},{"key":"10.1016\/j.jvoice.2024.03.001_bib40","doi-asserted-by":"crossref","unstructured":"Vidal J, Riera P, Ferrer L. Mispronunciation detection using self-supervised speech representations. SLaTe; 2023.","DOI":"10.21437\/SLaTE.2023-15"},{"key":"10.1016\/j.jvoice.2024.03.001_bib41","doi-asserted-by":"crossref","unstructured":"H. Song, S. Chen, Z. Chen, et al. Exploring wavlm on speech enhancement. 2022 IEEE Spoken Language Technology Workshop (SLT). IEEE, 2023:451\u2013457.","DOI":"10.1109\/SLT54892.2023.10023356"},{"key":"10.1016\/j.jvoice.2024.03.001_bib42","unstructured":"A. Dosovitskiy, L. Beyer, A. Kolesnikov, et al.\u00a0An image is worth 16\u00a0\u00d7\u00a016 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929; 2020."},{"key":"10.1016\/j.jvoice.2024.03.001_bib43","first-page":"61","article-title":"Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods","volume":"10","author":"Platt","year":"1999","journal-title":"Adv Large Margin Classif"},{"key":"10.1016\/j.jvoice.2024.03.001_bib44","series-title":"The Elements of Statistical Learning: Data Mining, Inference, and Prediction, Volume 2","author":"Hastie","year":"2009"},{"key":"10.1016\/j.jvoice.2024.03.001_bib45","doi-asserted-by":"crossref","unstructured":"M. Hirano and K.R. McCormick. Clinical examination of voice by minoru hirano; 1986.","DOI":"10.1121\/1.393788"}],"container-title":["Journal of Voice"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0892199724000729?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0892199724000729?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T21:11:59Z","timestamp":1783631519000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0892199724000729"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":45,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,7]]}},"alternative-id":["S0892199724000729"],"URL":"https:\/\/doi.org\/10.1016\/j.jvoice.2024.03.001","relation":{},"ISSN":["0892-1997"],"issn-type":[{"value":"0892-1997","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Automatic Voice Disorder Detection from a Practical Perspective","name":"articletitle","label":"Article Title"},{"value":"Journal of Voice","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jvoice.2024.03.001","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Published by Elsevier Inc. on behalf of The Voice Foundation.","name":"copyright","label":"Copyright"}]}}