{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T15:06:45Z","timestamp":1764688005542,"version":"3.37.3"},"reference-count":35,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012492","name":"Youth Innovation Promotion Association","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012492","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002367","name":"Chinese Academy of Sciences","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100015095","name":"Institute of Acoustics, Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["QYTS202011"],"award-info":[{"award-number":["QYTS202011"]}],"id":[{"id":"10.13039\/501100015095","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/lsp.2022.3190793","type":"journal-article","created":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T19:26:10Z","timestamp":1657740370000},"page":"1654-1658","source":"Crossref","is-referenced-by-count":5,"title":["An E2E-ASR-Based Iteratively-Trained Timestamp Estimator"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3466-6882","authenticated-orcid":false,"given":"Runyan","family":"Yang","sequence":"first","affiliation":[{"name":"Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2102-6061","authenticated-orcid":false,"given":"Gaofeng","family":"Cheng","sequence":"additional","affiliation":[{"name":"Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6838-5160","authenticated-orcid":false,"given":"Pengyuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6907-5770","authenticated-orcid":false,"given":"Yonghong","family":"Yan","sequence":"additional","affiliation":[{"name":"Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"89","article-title":"The aligner: Text to speech alignment using Markov models and a pronunciation dictionary","volume-title":"Proc. IEEE\/ESCA 2nd Workshop Speech Synth.","author":"Talkin","year":"1994"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1007\/11930334_18"},{"key":"ref3","first-page":"2042","article-title":"Weakly-supervised text-to-speech alignment confidence measure","volume-title":"Proc. 26th Int. Conf. Comput. Linguistics: Tech. Papers","author":"Serrire","year":"2016"},{"key":"ref4","first-page":"51","article-title":"Results of the 2006 spoken term detection evaluation","volume-title":"Proc. ACM SIGIR Workshop","author":"Fiscus","year":"2007"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/TASLP.2021.3120632"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1186\/s13636-021-00212-9"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.3115\/1289189.1289195"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1007\/978-3-540-30228-5_4"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.21437\/Interspeech.2011-815"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.21437\/Interspeech.2017-1386"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1109\/ICASSP.2018.8462105"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1109\/ASRU46091.2019.9003750"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1109\/ICASSP.2018.8461809"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1109\/ASRU.2017.8268937"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1109\/ICASSP40776.2020.9054715"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1109\/ICASSP39728.2021.9413803"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.21437\/Interspeech.2020-1059"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1007\/978-3-030-60276-5_27"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1145\/1143844.1143891"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1109\/ICASSP.2014.6854674"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1109\/ICASSP.2014.6854675"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1109\/JSTSP.2017.2763455"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1109\/TASLP.2020.2987752"},{"doi-asserted-by":"publisher","key":"ref24","DOI":"10.1109\/ICASSP.2016.7472621"},{"doi-asserted-by":"publisher","key":"ref25","DOI":"10.1016\/0167-6393(90)90010-7"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref27","first-page":"1","article-title":"The Kaldi speech recognition toolkit","volume-title":"Proc. Workshop Autom. Speech Recognit. Understanding IEEE Signal Process. Soc.","author":"Povey","year":"2011"},{"key":"ref28","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani","year":"2017"},{"doi-asserted-by":"publisher","key":"ref29","DOI":"10.1109\/ICASSP.2018.8462506"},{"doi-asserted-by":"publisher","key":"ref30","DOI":"10.21437\/Interspeech.2019-1938"},{"doi-asserted-by":"publisher","key":"ref31","DOI":"10.21437\/Interspeech.2018-1456"},{"doi-asserted-by":"publisher","key":"ref32","DOI":"10.21437\/Interspeech.2015-711"},{"key":"ref33","first-page":"23","article-title":"A new algorithm for data compression","volume":"12","author":"Gage","year":"1994","journal-title":"C. Users J."},{"key":"ref34","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. 3rd Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"doi-asserted-by":"publisher","key":"ref35","DOI":"10.21437\/Interspeech.2019-2680"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/97\/9686799\/09829287.pdf?arnumber=9829287","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T07:42:14Z","timestamp":1706773334000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9829287\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/lsp.2022.3190793","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"type":"print","value":"1070-9908"},{"type":"electronic","value":"1558-2361"}],"subject":[],"published":{"date-parts":[[2022]]}}}