{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T18:43:01Z","timestamp":1747680181497,"version":"3.33.0"},"reference-count":46,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,12,2]]},"DOI":"10.1109\/slt61566.2024.10832264","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:27Z","timestamp":1737052287000},"page":"1076-1082","source":"Crossref","is-referenced-by-count":1,"title":["Long-Form End-To-End Speech Translation VIA Latent Alignment Segmentation"],"prefix":"10.1109","author":[{"given":"Peter","family":"Pol\u00e1k","sequence":"first","affiliation":[{"name":"Charles University,Czechia"}]},{"given":"Ond\u0159ej","family":"Bojar","sequence":"additional","affiliation":[{"name":"Charles University,Czechia"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1992.225935"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s10590-008-9047-0"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-demos.32"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1017\/ATSIP.2018.6"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.661"},{"key":"ref6","first-page":"177","article-title":"Better punctuation prediction with dynamic conditional random fields","volume-title":"Proc. EMNLP","author":"Lu"},{"article-title":"Punctuation insertion for real-time spoken language translation","volume-title":"Proc. IWSLT","author":"Cho","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1320"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/97.736233"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-511"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-59"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11382"},{"key":"ref13","first-page":"12449","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-933"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.eacl-main.119"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-154"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1055"},{"key":"ref19","article-title":"Can neural machine translation do simultaneous translation?","author":"Cho","year":"2016","journal-title":"arXiv preprint arXiv:1606.02012"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2079"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.iwslt-1.1"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.iwslt-1.1"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.iwslt-1.10"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.iwslt-1.1"},{"key":"ref25","first-page":"55","article-title":"Beyond voice activity detection: Hybrid audio segmentation for direct speech translation","volume-title":"Proceedings of The Fourth International Conference on Natural Language and Speech Processing (ICNLSP 2021)","author":"Gaido"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1080\/17470215808416261"},{"key":"ref27","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2022-143","article-title":"Xls-r: Self-supervised cross-lingual speech representation learning at scale","volume-title":"arXiv preprint arXiv:2111.09296","author":"Babu"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.iwslt-1.9"},{"key":"ref30","article-title":"Sequence to sequence learning with neural networks","volume-title":"Advances in neural information processing systems","volume":"27","author":"Sutskever"},{"key":"ref31","article-title":"Neural machine translation by jointly learning to align and translate","author":"Bahdanau","year":"2014","journal-title":"arXiv preprint arXiv:1409.0473"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.iwslt-1.37"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2225"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"article-title":"Supervised sequence labelling with recurrent neural networks","year":"2008","author":"Graves","key":"ref35"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2020.101155"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054626"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383517"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1007"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-demo.38"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.19"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.58"},{"article-title":"Evaluating machine translation output with automatic sentence segmentation","volume-title":"Proc. IWSLT","author":"Matusov","key":"ref43"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6319"},{"article-title":"CUNI-KIT System for Smultaneous Speech Translation Task at IWSLT 2022","volume-title":"Proc. IWSLT","author":"Pol\u00e1k","key":"ref45"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.autosimtrans-1.2"}],"event":{"name":"2024 IEEE Spoken Language Technology Workshop (SLT)","start":{"date-parts":[[2024,12,2]]},"location":"Macao","end":{"date-parts":[[2024,12,5]]}},"container-title":["2024 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10830790\/10830793\/10832264.pdf?arnumber=10832264","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T07:42:07Z","timestamp":1737099727000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10832264\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/slt61566.2024.10832264","relation":{},"subject":[],"published":{"date-parts":[[2024,12,2]]}}}