{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,20]],"date-time":"2026-10-20T10:05:39Z","timestamp":1792490739643,"version":"4.5.0"},"reference-count":37,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T00:00:00Z","timestamp":1725408000000},"content-version":"vor","delay-in-days":3,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82071033"],"award-info":[{"award-number":["82071033"]}],"id":[{"id":"10.13039\/501100001809","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":[[2024,9]]},"DOI":"10.1016\/j.jvoice.2024.09.002","type":"journal-article","created":{"date-parts":[[2024,9,25]],"date-time":"2024-09-25T16:28:00Z","timestamp":1727281680000},"update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":35,"title":["Voice Disorder Classification Using Wav2vec 2.0 Feature Extraction"],"prefix":"10.1016","author":[{"given":"Jie","family":"Cai","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuliang","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianghao","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.jvoice.2024.09.002_bib1","doi-asserted-by":"crossref","first-page":"761.e1","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":"10.1016\/j.jvoice.2024.09.002_bib2","doi-asserted-by":"crossref","first-page":"551","DOI":"10.1016\/S0025-7125(16)30239-5","article-title":"Voice disorders","volume":"77","author":"Sataloff","year":"1993","journal-title":"Med Clin North Am"},{"key":"10.1016\/j.jvoice.2024.09.002_bib3","doi-asserted-by":"crossref","first-page":"343","DOI":"10.1002\/lary.22426","article-title":"Prevalence and causes of dysphonia in a large treatment-seeking population","volume":"122","author":"Cohen","year":"2012","journal-title":"Laryngoscope"},{"key":"10.1016\/j.jvoice.2024.09.002_bib4","doi-asserted-by":"crossref","first-page":"716","DOI":"10.1016\/j.jvoice.2014.02.008","article-title":"Voice disorders in teachers. A review","volume":"28","author":"Martins","year":"2014","journal-title":"J Voice"},{"key":"10.1016\/j.jvoice.2024.09.002_bib5","article-title":"Prevalence of work-related voice disorders in voice professionals: systematic review and meta-analysis","author":"Oliveira","year":"2022","journal-title":"J Voice"},{"key":"10.1016\/j.jvoice.2024.09.002_bib6","doi-asserted-by":"crossref","first-page":"975","DOI":"10.1111\/coa.13417","article-title":"Vocal fold nodules: a disorder of phonation organs or auditory feedback?","volume":"44","author":"Lee","year":"2019","journal-title":"Clin Otolaryngol"},{"key":"10.1016\/j.jvoice.2024.09.002_bib7","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/s11864-002-0036-x","article-title":"Early laryngeal cancer","volume":"3","author":"Hinerman","year":"2002","journal-title":"Curr Treat Options Oncol"},{"key":"10.1016\/j.jvoice.2024.09.002_bib8","first-page":"55","article-title":"Acoustic assessment","volume":"85","author":"Costello","year":"2020","journal-title":"Adv Otorhinolaryngol"},{"key":"10.1016\/j.jvoice.2024.09.002_bib9","doi-asserted-by":"crossref","first-page":"589","DOI":"10.1016\/j.otc.2019.03.002","article-title":"Components of voice evaluation","volume":"52","author":"Reghunathan","year":"2019","journal-title":"Otolaryngol Clin North Am"},{"key":"10.1016\/j.jvoice.2024.09.002_bib10","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1007\/s12070-020-01827-8","article-title":"Role of video laryngostroboscopy in benign disease of larynx","volume":"72","author":"Sachdeva","year":"2020","journal-title":"Indian J Otolaryngol Head Neck Surg"},{"key":"10.1016\/j.jvoice.2024.09.002_bib11","doi-asserted-by":"crossref","DOI":"10.2196\/46105","article-title":"Applied machine learning techniques to diagnose voice-affecting conditions and disorders: systematic literature review","volume":"25","author":"Idrisoglu","year":"2023","journal-title":"J Med Internet Res"},{"key":"10.1016\/j.jvoice.2024.09.002_bib12","doi-asserted-by":"crossref","DOI":"10.2196\/38472","article-title":"The effectiveness of supervised machine learning in screening and diagnosing voice disorders: systematic review and meta-analysis","volume":"24","author":"Al-Hussain","year":"2022","journal-title":"J Med Internet Res"},{"key":"10.1016\/j.jvoice.2024.09.002_bib13","doi-asserted-by":"crossref","first-page":"7958","DOI":"10.3934\/mbe.2020404","article-title":"Meta-analysis of voice disorders databases and applied machine learning techniques","volume":"17","author":"Syed","year":"2020","journal-title":"Math Biosci Eng"},{"key":"10.1016\/j.jvoice.2024.09.002_bib14","doi-asserted-by":"crossref","DOI":"10.1016\/j.amjoto.2021.103327","article-title":"Development of a machine-learning based voice disorder screening tool","volume":"43","author":"Reid","year":"2022","journal-title":"Am J Otolaryngol"},{"key":"10.1016\/j.jvoice.2024.09.002_bib15","doi-asserted-by":"crossref","unstructured":"Dhief F.T.A., Latiff N.M.A., Malik N.N.N.A., et al., Voice Pathology Detection Using Machine Learning Technique, 2020 IEEE 5th International Symposium on Telecommunication Technologies (ISTT), 2020, pp. 99-104. doi: 10.1109\/ISTT50966.2020.9279346.","DOI":"10.1109\/ISTT50966.2020.9279346"},{"key":"10.1016\/j.jvoice.2024.09.002_bib16","first-page":"1","article-title":"MFCC in audio signal processing for voice disorder: a review","volume":"83","author":"Sidhu","year":"2024","journal-title":"Multimed Tools Appl"},{"key":"10.1016\/j.jvoice.2024.09.002_bib17","doi-asserted-by":"crossref","first-page":"324","DOI":"10.1177\/000348940311200406","article-title":"Cepstral peak prominence: a more reliable measure of dysphonia","volume":"112","author":"Heman-Ackah","year":"2003","journal-title":"Ann Otol Rhinol Laryngol"},{"key":"10.1016\/j.jvoice.2024.09.002_bib18","doi-asserted-by":"crossref","first-page":"288.e15","DOI":"10.1016\/j.jvoice.2020.05.029","article-title":"Deep neural network for automatic classification of pathological voice signals","volume":"36","author":"Chen","year":"2022","journal-title":"J Voice"},{"key":"10.1016\/j.jvoice.2024.09.002_bib19","doi-asserted-by":"crossref","first-page":"16246","DOI":"10.1109\/ACCESS.2018.2816338","article-title":"Voice disorder identification by using machine learning techniques","volume":"6","author":"Verde","year":"2018","journal-title":"IEEE Access"},{"key":"10.1016\/j.jvoice.2024.09.002_bib20","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.2024.09.002_bib21","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.2024.09.002_bib22","first-page":"3465","article-title":"wav2vec: unsupervised pre-training for speech recognition","author":"Schneider","year":"2019","journal-title":"Interspeech"},{"key":"10.1016\/j.jvoice.2024.09.002_bib23","article-title":"wav2vec 2.0: a framework for self-supervised learning of speech representations","volume":"2006","author":"Baevski","year":"2020","journal-title":"arXiv"},{"key":"10.1016\/j.jvoice.2024.09.002_bib24","article-title":"A fine-tuned Wav2vec 2.0\/HuBERT benchmark for speech emotion recognition, speaker verification and spoken language understanding","author":"Wang","year":"2021","journal-title":"arXiv"},{"key":"10.1016\/j.jvoice.2024.09.002_bib25","doi-asserted-by":"crossref","first-page":"260","DOI":"10.2478\/msr-2023-0033","article-title":"Evaluating the performance of wav2vec embedding for Parkinson's disease detection","volume":"23","author":"Klemp\u00ed\u0159","year":"2023","journal-title":"Meas Sci Rev"},{"key":"10.1016\/j.jvoice.2024.09.002_bib26","doi-asserted-by":"crossref","first-page":"310","DOI":"10.1016\/j.compeleceng.2018.04.008","article-title":"A new database of healthy and pathological voices","volume":"68","author":"Cesari","year":"2018","journal-title":"Comput Electr Eng"},{"key":"10.1016\/j.jvoice.2024.09.002_bib27","unstructured":"wav2vec large.pt.\u00a0Accessed May 21, 2024. Available at: https:\/\/dl.fbaipublicfiles.com\/fairseq\/wav2vec\/wav2vec_large.pt."},{"key":"10.1016\/j.jvoice.2024.09.002_bib28","series-title":"Machine Learning","first-page":"101","article-title":"Chapter 6 - Support vector machine","author":"Pisner","year":"2020"},{"key":"10.1016\/j.jvoice.2024.09.002_bib29","doi-asserted-by":"crossref","first-page":"218","DOI":"10.21037\/atm.2016.03.37","article-title":"Introduction to machine learning: k-nearest neighbors","volume":"4","author":"Zhang","year":"2016","journal-title":"Ann Transl Med"},{"key":"10.1016\/j.jvoice.2024.09.002_bib30","article-title":"Deep neural decision trees","author":"Yang","year":"2018","journal-title":"arXiv"},{"key":"10.1016\/j.jvoice.2024.09.002_bib31","doi-asserted-by":"crossref","first-page":"31","DOI":"10.17849\/insm-47-01-31-39.1","article-title":"Random forest","volume":"47","author":"Rigatti","year":"2017","journal-title":"J Insur Med"},{"key":"10.1016\/j.jvoice.2024.09.002_bib32","doi-asserted-by":"crossref","unstructured":"Yadav S., Shukla S., Analysis of k-Fold Cross-Validation over Hold-Out Validation on Colossal Datasets for Quality Classification, 2016 IEEE 6th International Conference on Advanced Computing (IACC), 2016, pp. 78-83. doi:10.1109\/IACC.2016.25.","DOI":"10.1109\/IACC.2016.25"},{"key":"10.1016\/j.jvoice.2024.09.002_bib33","doi-asserted-by":"crossref","first-page":"122136","DOI":"10.1109\/ACCESS.2022.3223444","article-title":"Mel frequency cepstral coefficient and its applications: a review","volume":"10","author":"Abdul","year":"2022","journal-title":"IEEE Access"},{"key":"10.1016\/j.jvoice.2024.09.002_bib34","doi-asserted-by":"crossref","first-page":"46938","DOI":"10.1109\/ACCESS.2023.3275106","article-title":"A WAV2VEC2-based experimental study on self-supervised learning methods to improve child speech recognition","volume":"11","author":"Jain","year":"2023","journal-title":"IEEE Access"},{"key":"10.1016\/j.jvoice.2024.09.002_bib35","doi-asserted-by":"crossref","first-page":"9543","DOI":"10.1038\/s41598-024-60278-1","article-title":"Improving speech depression detection using transfer learning with wav2vec 2.0 in low-resource environments","volume":"14","author":"Zhang","year":"2024","journal-title":"Sci Rep"},{"key":"10.1016\/j.jvoice.2024.09.002_bib36","first-page":"3618","article-title":"Wav2vec2-based speech rating system for children with speech sound disorder","volume":"23","author":"Getman","year":"2022","journal-title":"Int Speech Commun Assoc (ISCA)"},{"key":"10.1016\/j.jvoice.2024.09.002_bib37","doi-asserted-by":"crossref","first-page":"932.e1","DOI":"10.1016\/j.jvoice.2020.03.009","article-title":"Voice disorder identification by using Hilbert-Huang transform (HHT) and K nearest neighbor (KNN)","volume":"35","author":"Chen","year":"2021","journal-title":"J Voice"}],"container-title":["Journal of Voice"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0892199724002935?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0892199724002935?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T19:44:35Z","timestamp":1777578275000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0892199724002935"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9]]},"references-count":37,"alternative-id":["S0892199724002935"],"URL":"https:\/\/doi.org\/10.1016\/j.jvoice.2024.09.002","relation":{},"ISSN":["0892-1997"],"issn-type":[{"value":"0892-1997","type":"print"}],"subject":[],"published":{"date-parts":[[2024,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Voice Disorder Classification Using Wav2vec 2.0 Feature Extraction","name":"articletitle","label":"Article Title"},{"value":"Journal of Voice","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jvoice.2024.09.002","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2024 The Authors. Published by Elsevier Inc. on behalf of The Voice Foundation.","name":"copyright","label":"Copyright"}]}}