{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T08:02:10Z","timestamp":1767772930943,"version":"3.37.3"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Research Fund of the Gebze Technical University","award":["2023-A-102-04"],"award-info":[{"award-number":["2023-A-102-04"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/taslp.2024.3473316","type":"journal-article","created":{"date-parts":[[2024,10,7]],"date-time":"2024-10-07T17:48:59Z","timestamp":1728323339000},"page":"4501-4510","source":"Crossref","is-referenced-by-count":2,"title":["Audio-Only Phonetic Segment Classification Using Embeddings Learned From Audio and Ultrasound Tongue Imaging Data"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4237-8442","authenticated-orcid":false,"given":"Ilhan","family":"Aytutuldu","sequence":"first","affiliation":[{"name":"Department of Computer Engineering, Gebze Technical University, Gebze, Türkiye"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6952-6735","authenticated-orcid":false,"given":"Yakup","family":"Genc","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, Gebze Technical University, Gebze, Türkiye"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8501-4812","authenticated-orcid":false,"given":"Yusuf Sinan","family":"Akgul","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, Gebze Technical University, Gebze, Türkiye"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1080\/02699200500113558"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683564"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1977.1162968"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1121\/1.428391"},{"article-title":"Employing speech recognition and capturing customer speech to improve customer service","year":"2005","author":"Gusler","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2012.10.003"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2598428"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472924"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1080\/17549507.2018.1513562"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3308561.3354606"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3023101"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3109\/02699206.2015.1016188"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1044\/2018_JSLHR-S-17-0360"},{"key":"ref14","first-page":"41","article-title":"UltraPhonix: Ultrasound visual biofeedback for the treatment of speech sound disorders","volume-title":"Proc. Ultrafest VIII,","author":"Cleland","year":"2017"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383619"},{"key":"ref16","article-title":"A new application of ultrasound to image tongue behaviour in cleft palate speech","volume-title":"Proc. Poster Presentation Craniofacial Soc. Great Britain Ireland Annu. Sci. Conf.","author":"Gibbon","year":"2005"},{"key":"ref17","first-page":"148","article-title":"Ultrasound technology and second language acquisition research","volume-title":"Proc. 8th Generative Approaches 2nd Lang. Acquisition Conf.","author":"Wilson","year":"2006"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1075\/sibil.36.15gic"},{"key":"ref19","first-page":"974","article-title":"Using ultrasound imaging to create augmented visual biofeedback for articulatory practice","volume-title":"Proc. Interspeech","author":"Annand","year":"2019"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-66562-7_25"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s11265-016-1148-z"},{"key":"ref22","first-page":"39","article-title":"A computer-based speech sound disorder screening system architecture","volume":"251","author":"Mahmut","year":"2018","journal-title":"Data, Inform. Technol.: Inspiration Improved Healthcare"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053973"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3229434.3229484"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3464385.3464745"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3791\/55123"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcomdis.2016.02.004"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.bandl.2013.11.001"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1044\/2014_JSLHR-S-14-0034"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1044\/1058-0360(2012\/12-0022)"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1044\/2019_PERS-SIG18-2018-0022"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3109\/17549507.2015.1126640"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1044\/2014_AJSLP-13-0035"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1017\/S0142716423000279"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-33676-9_36"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2019.103335"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2017.12.003"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/BF00133570"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/42.811315"},{"article-title":"Automatic tongue contour segmentation using deep learning","year":"2018","author":"Wen","key":"ref40"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1121\/1.4951024"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1080\/02699200500113616"},{"article-title":"Automatic tongue contour segmentation using deep learning","year":"2018","author":"Wen","key":"ref43"},{"article-title":"Seeing speech: An articulatory web resource for the study of phonetics","year":"2015","author":"Lawson","key":"ref44"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1736"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/BIBM47256.2019.8983002"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24319-6_19"},{"year":"2012","key":"ref48","article-title":"Articulate assistant advanced user guide: Version 2.14"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ist55454.2022.9827729"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.08.007"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1005"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2017.134"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref54","first-page":"689","article-title":"Multimodal deep learning","volume-title":"Proc. 28th Int. Conf. Mach. Learn.","author":"Ngiam","year":"2011"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1121\/1.426900"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.5070\/p7151050347"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.32473\/flairs.v35i.130658"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.55630\/sjc.2014.8.169-182"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2007-294"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6570655\/10304349\/10706879.pdf?arnumber=10706879","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,18]],"date-time":"2024-10-18T17:32:51Z","timestamp":1729272771000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10706879\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3473316","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"type":"print","value":"2329-9290"},{"type":"electronic","value":"2329-9304"}],"subject":[],"published":{"date-parts":[[2024]]}}}