{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:23:26Z","timestamp":1775229806866,"version":"3.50.1"},"reference-count":65,"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":"am","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":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["NSF IIS-RI 2006618"],"award-info":[{"award-number":["NSF IIS-RI 2006618"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Advanced Research Computing"},{"name":"Information and Technology Services"}],"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.2024.3485465","type":"journal-article","created":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T17:50:29Z","timestamp":1729705829000},"page":"4727-4740","source":"Crossref","is-referenced-by-count":9,"title":["Automatic Disfluency Detection From Untranscribed Speech"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-2360-0732","authenticated-orcid":false,"given":"Amrit","family":"Romana","sequence":"first","affiliation":[{"name":"University of Michigan, Ann Arbor, MI, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3111-5375","authenticated-orcid":false,"given":"Kazuhito","family":"Koishida","sequence":"additional","affiliation":[{"name":"Microsoft Corporation, Redmond, WA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1870-6063","authenticated-orcid":false,"given":"Emily Mower","family":"Provost","sequence":"additional","affiliation":[{"name":"University of Michigan, Ann Arbor, MI, USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1749-818X.2008.00068.x"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2008-360"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-114"},{"key":"ref4","first-page":"1907","article-title":"Automatically detecting errors and disfluencies in read speech to predict cognitive impairment in people with Parkinson\u2019s disease","volume-title":"Proc. Interspeech","author":"Romana","year":"2021"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1044\/cicsd_24_S_27"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.jfludis.2006.02.002"},{"key":"ref7","volume-title":"SSI-4: Stuttering Severity Instrument","author":"Riley","year":"2009"},{"key":"ref8","first-page":"1681","article-title":"Identification of primary and collateral tracks in stuttered speech","volume-title":"Proc. Conf. Lang. Resour. Eval.","author":"Riad","year":"2020"},{"key":"ref9","first-page":"1363","article-title":"Automatic correction of stutter in disfluent speech","volume-title":"Procedia Comput. Sci.","volume":"171","author":"Arjun","year":"2020"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2006"},{"key":"ref11","first-page":"6798","article-title":"Sep-28 k: A dataset for stuttering event detection from podcasts with people who stutter","volume-title":"Proc. IEEE Int. Conf. Acoust. Speech Signal Process.","author":"Lea","year":"2021"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581224"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-351"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10971"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095629"},{"key":"ref17","first-page":"12449","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Conf. Neural Inform. Process. Syst.","volume":"33","author":"Baevski","year":"2020"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10908"},{"key":"ref19","first-page":"1","article-title":"Measurements of oral reading and speaking rate and disfluency of adult male and female stutterers and nonstutterers","volume":"7","author":"Johnson","year":"1961","journal-title":"J. Speech Hear. Disord."},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413618"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3115\/1620853.1620885"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-604"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-603"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1247"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPS-ISA48467.2019.00021"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462562"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1336"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d18-1490"},{"key":"ref29","first-page":"3529","article-title":"Semi-supervised disfluency detection","volume-title":"Proc. Int. Conf. Comput. Linguistics","author":"Wang","year":"2018"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6456"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1374"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2946594"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCWAMTIP51612.2020.9317379"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1111\/j.1532-5415.2005.53221.x"},{"key":"ref35","article-title":"Deep speech: Scaling up end-to-end speech recognition","author":"Hannun","year":"2014"},{"key":"ref36","article-title":"Speech framework","year":"2022"},{"key":"ref37","first-page":"91","article-title":"Prosodic features of four types of disfluencies","volume-title":"Proc. Disfluency Spontaneous Speech Workshop","author":"Savova","year":"2003"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2012-215"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Eurospeech.1997-626"},{"issue":"2","key":"ref40","first-page":"619","article-title":"Phonetic consequences of speech disfluency","volume-title":"Proc. Int. Congr. Phonetic Sci.","volume":"1","author":"Shriberg","year":"1999"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1029"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1008"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1992.225858"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747236"},{"key":"ref45","article-title":"Speechstew: Simply mix all available speech recognition data to train one large neural network","author":"Chan","year":"2021"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-11"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/ICSLP.1998-588"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3134"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.3115\/1073336.1073352"},{"key":"ref50","first-page":"8026","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Conf. Neural Inform. Process. Syst.","volume":"32","author":"Paszke","year":"2019"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref56","first-page":"187","article-title":"KenLM: Faster and smaller language model queries","volume-title":"Proc. Workshop Statist. Mach. Transl.","author":"Heafield","year":"2011"},{"key":"ref57","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2022"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18637\/jss.v031.i07"},{"key":"ref59","article-title":"whisper-timestamped","author":"Louradour","year":"2023"},{"key":"ref60","article-title":"Azure speech to text","year":"2022"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-4012"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3067460"},{"key":"ref65","article-title":"Best practices for noise-based augmentation to improve the performance of deployable speech-based emotion recognition systems","author":"Jaiswal","year":"2021"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/6570655\/10304349\/10731569-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6570655\/10304349\/10731569.pdf?arnumber=10731569","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T01:31:08Z","timestamp":1732671068000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10731569\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":65,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3485465","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}