{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T14:21:10Z","timestamp":1787062870069,"version":"build-2736575974"},"reference-count":21,"publisher":"Elsevier BV","issue":"3","license":[{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"}],"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":[[2025,5]]},"DOI":"10.1016\/j.jvoice.2024.11.037","type":"journal-article","created":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T23:51:51Z","timestamp":1733529111000},"page":"574-576","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"title":["Have We Solved Glottis Segmentation? Review and Commentary"],"prefix":"10.1016","volume":"39","author":[{"given":"Andreas M.","family":"Kist","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"D..llinger","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.jvoice.2024.11.037_bib1","doi-asserted-by":"crossref","first-page":"E654","DOI":"10.1002\/lary.28475","article-title":"Intersegmenter variability in high-speed laryngoscopy-based glottal area waveform measures","volume":"130","author":"Maryn","year":"2020","journal-title":"Laryngoscope"},{"key":"10.1016\/j.jvoice.2024.11.037_bib2","doi-asserted-by":"crossref","first-page":"400","DOI":"10.1016\/j.media.2007.04.005","article-title":"Clinically evaluated procedure for the reconstruction of vocal fold vibrations from endoscopic digital high-speed videos","volume":"11","author":"Lohscheller","year":"2007","journal-title":"Med Image Anal"},{"key":"10.1016\/j.jvoice.2024.11.037_bib3","doi-asserted-by":"crossref","first-page":"795","DOI":"10.1109\/TBME.2014.2364862","article-title":"Fully automated glottis segmentation in endoscopic videos using local color and shape features of glottal regions","volume":"62","author":"Gloger","year":"2015","journal-title":"IEEE Trans Biomed Eng"},{"key":"10.1016\/j.jvoice.2024.11.037_bib4","doi-asserted-by":"crossref","first-page":"e0227791","DOI":"10.1371\/journal.pone.0227791","article-title":"Fully automatic segmentation of glottis and vocal folds in endoscopic laryngeal high-speed videos using a deep convolutional LSTM network","volume":"15","author":"Fehling","year":"2020","journal-title":"PLOS One"},{"key":"10.1016\/j.jvoice.2024.11.037_bib5","doi-asserted-by":"crossref","first-page":"483","DOI":"10.1007\/s11548-018-01910-0","article-title":"A dataset of laryngeal endoscopic images with comparative study on convolution neural network-based semantic segmentation","volume":"14","author":"Laves","year":"2019","journal-title":"Int J CARS"},{"key":"10.1016\/j.jvoice.2024.11.037_bib6","first-page":"186","article-title":"BAGLS, a multihospital benchmark for automatic glottis segmentation","volume":"7","author":"G..mez","year":"2020","journal-title":"SciData"},{"key":"10.1016\/j.jvoice.2024.11.037_bib7","unstructured":"Ronneberger O, Fischer P, BroxT. U-Net: Convolutional Networks for Biomedical Image Segmentation, arXiv: 1505.04597 [cs], 2015, Zugegriffen: 9. November 2018. [Online]. Available at http:\/\/arxiv.org\/abs\/1505.04597."},{"key":"10.1016\/j.jvoice.2024.11.037_bib8","doi-asserted-by":"crossref","first-page":"14292","DOI":"10.1038\/s41598-022-17764-1","article-title":"A single latent channel is sufficient for biomedical glottis segmentation","volume":"12","author":"Kist","year":"2022","journal-title":"Sci Rep"},{"key":"10.1016\/j.jvoice.2024.11.037_bib9","doi-asserted-by":"crossref","first-page":"103116","DOI":"10.1016\/j.bspc.2021.103116","article-title":"Automatic glottis segmentation for laryngeal endoscopic images based on U-Net","volume":"71","author":"Ding","year":"2022","journal-title":"Biomed Signal Process Control"},{"key":"10.1016\/j.jvoice.2024.11.037_bib10","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1016\/j.jvoice.2020.10.017","article-title":"Spatial segmentation for laryngeal high-speed videoendoscopy in connected speech","volume":"37","author":"Yousef","year":"2023","journal-title":"J Voice"},{"key":"10.1016\/j.jvoice.2024.11.037_bib11","doi-asserted-by":"crossref","first-page":"13760","DOI":"10.1038\/s41598-021-93149-0","article-title":"OpenHSV: an open platform for laryngeal high-speed videoendoscopy","volume":"11","author":"Kist","year":"2021","journal-title":"Sci Rep"},{"key":"10.1016\/j.jvoice.2024.11.037_bib12","doi-asserted-by":"crossref","first-page":"e0266989","DOI":"10.1371\/journal.pone.0266989","article-title":"Long-term performance assessment of fully automatic biomedical glottis segmentation at the point of care","volume":"17","author":"Groh","year":"2022","journal-title":"Plos One"},{"key":"10.1016\/j.jvoice.2024.11.037_bib13","doi-asserted-by":"crossref","first-page":"9791","DOI":"10.3390\/app12199791","article-title":"Re-training of convolutional neural networks for glottis segmentation in endoscopic high-speed videos","volume":"12","author":"D..llinger u. a","year":"2022","journal-title":"Appl Sci"},{"key":"10.1016\/j.jvoice.2024.11.037_bib14","first-page":"33","article-title":"Clinical implementation of laryngeal high-speed videoendoscopy: challenges and evolution","volume":"60","author":"Deliyski","year":"2008","journal-title":"FPL"},{"key":"10.1016\/j.jvoice.2024.11.037_bib15","doi-asserted-by":"crossref","first-page":"139356","DOI":"10.1109\/ACCESS.2020.3012722","article-title":"Efficient biomedical image segmentation on edgeTPUs at point of care","volume":"8","author":"Kist","year":"2020","journal-title":"IEEE Access"},{"key":"10.1016\/j.jvoice.2024.11.037_bib16","doi-asserted-by":"crossref","unstructured":"Kist AM, Razi S, Groh R, et al, Predicting semantic segmentation quality in laryngeal endoscopy images, 15. November 2024, bioRxiv. doi: 10.1101\/2024.11.14.623604.","DOI":"10.1101\/2024.11.14.623604"},{"key":"10.1016\/j.jvoice.2024.11.037_bib17","unstructured":"Wevosys, lingWAVES 4 High Speed Videoendoscopy (HSV). [Online]. Available at https:\/\/www.wevosys.com\/products\/lingwaves4\/lingwaves4_high_speed_videoendoscopy.html."},{"key":"10.1016\/j.jvoice.2024.11.037_bib18","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3453476","article-title":"Federated learning for smart healthcare: a survey","volume":"55","author":"Nguyen","year":"2022","journal-title":"ACM Comput Surv (Csur)"},{"key":"10.1016\/j.jvoice.2024.11.037_bib19","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41598-020-77216-6","article-title":"Rethinking glottal midline detection","volume":"10","author":"Kist","year":"2020","journal-title":"Sci Rep"},{"key":"10.1016\/j.jvoice.2024.11.037_bib20","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1109\/JTEHM.2023.3237859","article-title":"Glottisnetv2: temporal glottal midline detection using deep convolutional neural networks","volume":"11","author":"Kruse","year":"2023","journal-title":"IEEE J Trans Eng Health Med"},{"key":"10.1016\/j.jvoice.2024.11.037_bib21","doi-asserted-by":"crossref","first-page":"13132","DOI":"10.1038\/s41598-024-62598-8","article-title":"Biomechanics of sound production in high-pitched classical singing","volume":"14","author":"Echternach","year":"2024","journal-title":"Sci Rep"}],"container-title":["Journal of Voice"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S089219972400420X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S089219972400420X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T19:49:03Z","timestamp":1775072943000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S089219972400420X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5]]},"references-count":21,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2025,5]]}},"alternative-id":["S089219972400420X"],"URL":"https:\/\/doi.org\/10.1016\/j.jvoice.2024.11.037","relation":{},"ISSN":["0892-1997"],"issn-type":[{"value":"0892-1997","type":"print"}],"subject":[],"published":{"date-parts":[[2025,5]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Have We Solved Glottis Segmentation? Review and Commentary","name":"articletitle","label":"Article Title"},{"value":"Journal of Voice","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jvoice.2024.11.037","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"simple-article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 The Voice Foundation. Published by Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}]}}