{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T15:52:05Z","timestamp":1789055525859,"version":"build-2803163510"},"reference-count":48,"publisher":"Elsevier BV","issue":"4","license":[{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"}],"funder":[{"DOI":"10.13039\/100007709","name":"Michigan State University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007709","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000055","name":"National Institute on Deafness and Other Communication Disorders","doi-asserted-by":"publisher","award":["K01DC017751"],"award-info":[{"award-number":["K01DC017751"]}],"id":[{"id":"10.13039\/100000055","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["clinicalkey.fr","clinicalkey.jp","clinicalkey.es","clinicalkey.com.au","clinicalkey.com","jvoice.org","elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Voice"],"published-print":{"date-parts":[[2024,7]]},"DOI":"10.1016\/j.jvoice.2022.01.028","type":"journal-article","created":{"date-parts":[[2022,3,16]],"date-time":"2022-03-16T01:37:44Z","timestamp":1647394664000},"page":"951-962","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":14,"title":["Detection of Vocal Fold Image Obstructions in High-Speed Videoendoscopy During Connected Speech in Adductor Spasmodic Dysphonia: A Convolutional Neural Networks Approach"],"prefix":"10.1016","volume":"38","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4038-1138","authenticated-orcid":false,"given":"Ahmed M.","family":"Yousef","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9025-6047","authenticated-orcid":false,"given":"Dimitar D.","family":"Deliyski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stephanie R.C.","family":"Zacharias","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7310-8456","authenticated-orcid":false,"given":"Maryam","family":"Naghibolhosseini","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.jvoice.2022.01.028_bib0001","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1177\/000348940811700301","article-title":"Reliability of the perceptual evaluation of adductor spasmodic dysphonia","volume":"117","author":"Chetri","year":"2008","journal-title":"An Otol Rhinol Laryngol"},{"key":"10.1016\/j.jvoice.2022.01.028_bib0002","doi-asserted-by":"crossref","first-page":"311","DOI":"10.1097\/01.mlg.0000154739.48314.ee","article-title":"Task specificity in adductor spasmodic dysphonia versus muscle tension dysphonia","volume":"115","author":"Roy","year":"2005","journal-title":"The Laryngoscope"},{"key":"10.1016\/j.jvoice.2022.01.028_bib0003","doi-asserted-by":"crossref","first-page":"718","DOI":"10.1002\/lary.24362","article-title":"Automated acoustic analysis of task dependency in adductor spasmodic dysphonia versus muscle tension dysphonia","volume":"124","author":"Roy","year":"2014","journal-title":"The Laryngoscope"},{"key":"10.1016\/j.jvoice.2022.01.028_bib0004","doi-asserted-by":"crossref","first-page":"469","DOI":"10.1044\/1092-4388(2002\/037)","article-title":"Botox treatment in adductor spasmodic dysphonia: a meta-analysis","volume":"45","author":"Boutsen","year":"2002","journal-title":"J Sp Lang Hear Res"},{"key":"10.1016\/j.jvoice.2022.01.028_bib0005","doi-asserted-by":"crossref","first-page":"428","DOI":"10.3109\/00016489309135839","article-title":"Muscle misuse voice disorders: description and classification","volume":"113","author":"Morrison","year":"1993","journal-title":"Acta Otolaryngol"},{"key":"10.1016\/j.jvoice.2022.01.028_bib0006","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1080\/02699200050023994","article-title":"Analysing vocal quality of connected speech using Kay's computerized speech lab: a preliminary finding","volume":"14","author":"Yiu","year":"2000","journal-title":"Clin Linguist & Phon"},{"key":"10.1016\/j.jvoice.2022.01.028_bib0007","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1159\/000077798","article-title":"Acoustic and perceptual parameters relating to connected speech are more reliable measures of hoarseness than parameters relating to sustained vowels","volume":"66","author":"Halberstam","year":"2004","journal-title":"ORL"},{"key":"10.1016\/j.jvoice.2022.01.028_bib0008","doi-asserted-by":"crossref","first-page":"540","DOI":"10.1016\/j.jvoice.2008.12.014","article-title":"Toward improved ecological validity in the acoustic measurement of overall voice quality: combining continuous speech and sustained vowels","volume":"24","author":"Maryn","year":"2010","journal-title":"J Voice"},{"key":"10.1016\/j.jvoice.2022.01.028_bib0009","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1044\/vvd22.2.57","article-title":"The acoustic assessment of voice in continuous speech","volume":"22","author":"Lowell","year":"2012","journal-title":"SIG 3 Perspect Voice Voice Dis"},{"key":"10.1016\/j.jvoice.2022.01.028_bib0010","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41598-021-99948-9","article-title":"Comparative analysis of high-speed videolaryngoscopy images and sound data simultaneously acquired from rigid and flexible laryngoscope: a pilot study","volume":"11","author":"Pietruszewska","year":"2021","journal-title":"Sci Rep"},{"key":"10.1016\/j.jvoice.2022.01.028_bib0011","doi-asserted-by":"crossref","first-page":"413","DOI":"10.1177\/000348940811700603","article-title":"Comparison of high-speed digital imaging with stroboscopy for laryngeal imaging of glottal disorders","volume":"117","author":"Patel","year":"2008","journal-title":"Ann Otol Rhinol Laryngol"},{"key":"10.1016\/j.jvoice.2022.01.028_bib0012","doi-asserted-by":"crossref","first-page":"829","DOI":"10.1177\/0003489416656205","article-title":"Comparison of videostroboscopy and high-speed videoendoscopy in evaluation of supraglottic phonation","volume":"125","author":"Zacharias","year":"2016","journal-title":"Ann Otol Rhinol Laryngol"},{"key":"10.1016\/j.jvoice.2022.01.028_bib0013","series-title":"Laryngeal High-Speed Videoendoscopy, in: Laryngeal Evaluation: Indirect Laryngoscopy to High-Speed Digital Imaging","first-page":"243","author":"Deliyski","year":"2010"},{"key":"10.1016\/j.jvoice.2022.01.028_bib0014","doi-asserted-by":"crossref","first-page":"EL82","DOI":"10.1121\/1.4773200","article-title":"Vocal fold vibrations at high soprano fundamental frequencies","volume":"133","author":"Echternach","year":"2013","journal-title":"J Acoust Soc Am"},{"key":"10.1016\/j.jvoice.2022.01.028_bib0015","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1044\/vvd17.1.12","article-title":"Clinical feasibility of high-speed videoendoscopy","volume":"17","author":"Deliyski","year":"2007","journal-title":"SIG 3 perspectives on voice and voice disorders"},{"key":"10.1016\/j.jvoice.2022.01.028_bib0016","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1159\/000111802","article-title":"Clinical implementation of laryngeal high-speed videoendoscopy: challenges and evolution","volume":"60","author":"Deliyski","year":"2007","journal-title":"Folia Phoniatr. et Logop"},{"key":"10.1016\/j.jvoice.2022.01.028_bib0017","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1097\/MOO.0b013e3283395dd4","article-title":"State of the art laryngeal imaging: research and clinical implications","volume":"18","author":"Deliyski","year":"2010","journal-title":"Curr Opin Otolaryngol Head Neck Surg"},{"key":"10.1016\/j.jvoice.2022.01.028_bib0018","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1159\/000111802","article-title":"Clinical imple mentation of laryngeal high-speed videoendoscopy: challenges and evolution","volume":"60","author":"Deliyski","year":"2008","journal-title":"Folia Phoniatrica et Logopaedica"},{"key":"10.1016\/j.jvoice.2022.01.028_bib0019","first-page":"25","article-title":"Objective measures of stroboscopy and high speed video","volume":"85","author":"Woo","year":"2020","journal-title":"Adv Otorhinolaryngol"},{"key":"10.1016\/j.jvoice.2022.01.028_bib0020","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1044\/1092-4388(2010\/10-0026)","article-title":"Automated measurement of vocal fold vibratory asymmetry from high-speed videoendoscopy recordings","volume":"54","author":"Mehta","year":"2011","journal-title":"J Speech Lang Hear Res"},{"key":"10.1016\/j.jvoice.2022.01.028_bib0021","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1016\/j.bspc.2014.11.007","article-title":"Experimental investigation on minimum frame rate requirements of high-speed videoendoscopy for clinical voice assessment","volume":"17","author":"Deliyski","year":"2015","journal-title":"Biomed Signal Process Control"},{"key":"10.1016\/j.jvoice.2022.01.028_bib0022","doi-asserted-by":"crossref","first-page":"326","DOI":"10.1121\/1.3514536","article-title":"Observation and analysis of in vivo vocal fold tissue instabilities produced by nonlinear source-filter coupling: a case study","volume":"129","author":"Za\u00f1artu","year":"2011","journal-title":"J Acoust Soc Am"},{"key":"10.1016\/j.jvoice.2022.01.028_bib0023","first-page":"105","volume":"12","author":"Mehta","year":"2015"},{"key":"10.1016\/j.jvoice.2022.01.028_bib0024","doi-asserted-by":"crossref","first-page":"256.e1","DOI":"10.1016\/j.jvoice.2017.05.014","article-title":"Temporal segmentation for laryngeal high-speed videoendoscopy in connected speech","volume":"32","author":"Naghibolhosseini","year":"2018","journal-title":"J Voice"},{"key":"10.1016\/j.jvoice.2022.01.028_bib0025","article-title":"Spatial segmentation for laryngeal high-speed videoendoscopy in connected speech","author":"Yousef","year":"2020","journal-title":"J Voice"},{"key":"10.1016\/j.jvoice.2022.01.028_bib0026","doi-asserted-by":"crossref","first-page":"1179","DOI":"10.3390\/app11031179","article-title":"A hybrid machine-learning-based method for analytic representation of the vocal fold edges during connected speech","volume":"11","author":"Yousef","year":"2021","journal-title":"Appl Sci"},{"key":"10.1016\/j.jvoice.2022.01.028_bib0027","series-title":"14th International Conference on Advances in Quantitative Laryngology, Voice and Speech Research (AQL)","article-title":"Automated detection and segmentation of glottal area using deep-learning neural networks in high-speed videoendoscopy during connected speech","author":"Yousef","year":"2021"},{"key":"10.1016\/j.jvoice.2022.01.028_bib0028","series-title":"Proceedings of the 10th International Workshop on Models and Analysis of Vocal Emissions for Biomedical Applications MAVEBA","article-title":"A method for analysis of the vocal fold vibrations in connected speech using laryngeal imaging","author":"Naghibolhosseini","year":"2017"},{"key":"10.1016\/j.jvoice.2022.01.028_bib0048","doi-asserted-by":"crossref","DOI":"10.1044\/2022_JSLHR-21-00540","article-title":"A Deep Learning Approach for Quantifying Vocal Fold Dynamics during Connected Speech using Laryngeal High-Speed Videoendoscopy","author":"Yousef","year":"2022","journal-title":"J Speech Lang Hear Res"},{"key":"10.1016\/j.jvoice.2022.01.028_bib0029","doi-asserted-by":"crossref","DOI":"10.1121\/1.5067811","article-title":"Studying vocal fold non-stationary behavior during connected speech using high-speed videoendoscopy","volume":"144","author":"Naghibolhosseini","year":"2018","journal-title":"J Acoust Soc Am"},{"key":"10.1016\/j.jvoice.2022.01.028_bib0030","unstructured":"M Naghibolhosseini, N Heinz, C Brown, et al. \u201cGlottal attack time and glottal offset time comparison between vocally normal speakers and patients with adductor spasmodic dysphonia during connected speech,\u201d in 50th Anniversary Symposium: Care of the Professional Voice, Philadelphia PA, 2021."},{"key":"10.1016\/j.jvoice.2022.01.028_bib0031","series-title":"The 11th International Conference on Voice Physiology and Biomechanics","article-title":"Glottal attack time in connected speech","author":"Naghibolhosseini","year":"2018"},{"key":"10.1016\/j.jvoice.2022.01.028_bib0032","unstructured":"C Brown, M Naghibolhosseini, SRC Zacharias et al. \u201cInvestigation of high-speed videoendoscopy during connected speech in norm and neurogenic voice disorder,\u201d in Michigan Speech-Language-Hearing Association (MSHA) Annual Conference, East Lansing, MI, 2019."},{"key":"10.1016\/j.jvoice.2022.01.028_bib0033","doi-asserted-by":"crossref","first-page":"1123","DOI":"10.1097\/MLG.0b013e318041f70c","article-title":"Stroboscopy versus high-speed glottography: a comparative study","volume":"117","author":"Olthoff","year":"2007","journal-title":"The Laryngo scope"},{"key":"10.1016\/j.jvoice.2022.01.028_bib0034","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1016\/j.jvoice.2017.08.017","article-title":"Investigation of flexible high-speed video nasolaryngoscopy","volume":"32","author":"Popolo","year":"2018","journal-title":"J Voice"},{"key":"10.1016\/j.jvoice.2022.01.028_bib0035","doi-asserted-by":"crossref","first-page":"1101","DOI":"10.1001\/jama.2018.11100","article-title":"Deep learning \u2014 a technology with the potential to transform health care","volume":"320","author":"Hinton","year":"2018","journal-title":"J Am Med Assoc"},{"key":"10.1016\/j.jvoice.2022.01.028_bib0036","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1038\/s41591-018-0316-z","article-title":"A guide to deep learning in healthcare","volume":"25","author":"Esteva","year":"2019","journal-title":"Nat Med"},{"key":"10.1016\/j.jvoice.2022.01.028_bib0037","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1016\/j.cmpb.2018.01.030","article-title":"Learning-based classification of informative laryngoscopic frames","volume":"158","author":"Moccia","year":"2018","journal-title":"Comput Methods Programs Biomed"},{"key":"10.1016\/j.jvoice.2022.01.028_bib0038","doi-asserted-by":"crossref","first-page":"1225","DOI":"10.1007\/s11517-020-02127-7","article-title":"Transfer learning for informative-frame selection in laryngoscopic videos through learned features","volume":"58","author":"Patrini","year":"2020","journal-title":"Med Biol Eng Comput"},{"key":"10.1016\/j.jvoice.2022.01.028_bib0039","doi-asserted-by":"crossref","unstructured":"A Galdran, P Costa and A Campilho, \u201cReal-time informative laryngoscopic frame classification with pre-trained convolutional neural networks,\u201d In: 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), Venezia, Italy2019.","DOI":"10.1109\/ISBI.2019.8759511"},{"key":"10.1016\/j.jvoice.2022.01.028_bib0040","doi-asserted-by":"crossref","first-page":"E686","DOI":"10.1002\/lary.28539","article-title":"Automatic recognition of laryngoscopic images using a deep-learning technique","volume":"130","author":"Ren","year":"2020","journal-title":"The Laryngoscope"},{"key":"10.1016\/j.jvoice.2022.01.028_bib0041","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1016\/j.ebiom.2019.08.075","article-title":"Computer-aided diagnosis of laryngeal cancer via deep learning based on laryngoscopic images","volume":"48","author":"Xiong","year":"2019","journal-title":"EBioMedicine"},{"key":"10.1016\/j.jvoice.2022.01.028_bib0042","doi-asserted-by":"crossref","first-page":"2558","DOI":"10.1002\/lary.29595","article-title":"Diagnostic accuracies of laryngeal diseases using a convolutional neural network-based image classification system","volume":"131","author":"Cho","year":"2021","journal-title":"The Laryngoscope"},{"key":"10.1016\/j.jvoice.2022.01.028_bib0043","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","article-title":"ImageNet large scale visual recognition challenge","volume":"115","author":"Russakovsky","year":"2015","journal-title":"Int J Comput Vis"},{"key":"10.1016\/j.jvoice.2022.01.028_bib0044","doi-asserted-by":"crossref","first-page":"653","DOI":"10.1007\/s10120-018-0793-2","article-title":"Application of artificial intelligence using a convolutional neural network for detecting gastric cancer in endoscopic images","volume":"21","author":"Hirasawa","year":"2018","journal-title":"Gastric Cancer"},{"key":"10.1016\/j.jvoice.2022.01.028_bib0045","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1109\/JBHI.2016.2637004","article-title":"Integrating online and offline three-dimensional deep learning for automated polyp detection in colonoscopy videos","volume":"21","author":"Yu","year":"2017","journal-title":"IEEE J Biomed Health Inform"},{"key":"10.1016\/j.jvoice.2022.01.028_bib0046","series-title":"Int. Conf. Med. Image Comp. Comp.-ass. Interv.","article-title":"U-Net: convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015"},{"key":"10.1016\/j.jvoice.2022.01.028_bib0047","unstructured":"DP Kingma and J Ba, Adam: a method for stochastic optimization,arXiv preprint arXiv: 1412.6980., 2014."}],"container-title":["Journal of Voice"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0892199722000273?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0892199722000273?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T20:53:47Z","timestamp":1728939227000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0892199722000273"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7]]},"references-count":48,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024,7]]}},"alternative-id":["S0892199722000273"],"URL":"https:\/\/doi.org\/10.1016\/j.jvoice.2022.01.028","relation":{},"ISSN":["0892-1997"],"issn-type":[{"value":"0892-1997","type":"print"}],"subject":[],"published":{"date-parts":[[2024,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Detection of Vocal Fold Image Obstructions in High-Speed Videoendoscopy During Connected Speech in Adductor Spasmodic Dysphonia: A Convolutional Neural Networks Approach","name":"articletitle","label":"Article Title"},{"value":"Journal of Voice","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jvoice.2022.01.028","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2022 The Voice Foundation. Published by Elsevier Inc. All rights reserved.","name":"copyright","label":"Copyright"}]}}