{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:29:46Z","timestamp":1775230186145,"version":"3.50.1"},"reference-count":60,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100002347","name":"Federal Ministry of Education and Research BMBF","doi-asserted-by":"publisher","award":["03ZUll06DA"],"award-info":[{"award-number":["03ZUll06DA"]}],"id":[{"id":"10.13039\/501100002347","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,1,9]]},"DOI":"10.1109\/slt54892.2023.10022818","type":"proceedings-article","created":{"date-parts":[[2023,1,27]],"date-time":"2023-01-27T18:54:03Z","timestamp":1674845643000},"page":"229-236","source":"Crossref","is-referenced-by-count":9,"title":["Monotonic Segmental Attention for Automatic Speech Recognition"],"prefix":"10.1109","author":[{"given":"Albert","family":"Zeyer","sequence":"first","affiliation":[{"name":"RWTH Aachen University,Human Language Technology and Pattern Recognition,Computer Science Department,Aachen,Germany,52062"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Robin","family":"Schmitt","sequence":"additional","affiliation":[{"name":"RWTH Aachen University,Human Language Technology and Pattern Recognition,Computer Science Department,Aachen,Germany,52062"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Zhou","sequence":"additional","affiliation":[{"name":"RWTH Aachen University,Human Language Technology and Pattern Recognition,Computer Science Department,Aachen,Germany,52062"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ralf","family":"Schluter","sequence":"additional","affiliation":[{"name":"RWTH Aachen University,Human Language Technology and Pattern Recognition,Computer Science Department,Aachen,Germany,52062"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hermann","family":"Ney","sequence":"additional","affiliation":[{"name":"RWTH Aachen University,Human Language Technology and Pattern Recognition,Computer Science Department,Aachen,Germany,52062"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.neuro.26.041002.131047"},{"key":"ref2","first-page":"577","article-title":"Attention-based models for speech recognition","author":"Chorowski","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1616"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1488"},{"key":"ref7","article-title":"Analysis of positional encodings for neural machine translation","volume-title":"IWSLT","author":"Rosendahl"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003913"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003854"},{"key":"ref10","article-title":"Monotonic chunkwise attention","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Chiu","year":"2018"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2218"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1126"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d15-1166"},{"key":"ref15","first-page":"431","article-title":"Local monotonic attention mechanism for end-to-end speech and language processing","volume-title":"IJCNLP","volume":"1","author":"Tjandra","year":"2017"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682224"},{"key":"ref17","first-page":"5067","article-title":"An online sequence-to-sequence model using partial conditioning","author":"Jaitly","year":"2016","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref18","first-page":"2837","article-title":"Online and linear-time attention by enforcing monotonic alignments","volume-title":"Proceedings of the 34th International Conference on Machine Learning","author":"Raffel"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2879"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3031480"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.31390\/gradschool_dissertations.4601"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-751"},{"key":"ref23","article-title":"End-to-end continuous speech recognition using attention-based recurrent NN: first results","author":"Chorowski","year":"2014","journal-title":"Preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref25","article-title":"Sequence transduction with recurrent neural networks","author":"Graves","year":"2012","journal-title":"Preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1048"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683510"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003920"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2018"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1341"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054188"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/89.536930"},{"key":"ref35","article-title":"Segmental recurrent neural networks","author":"Kong","year":"2016","journal-title":"ICLR"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-40"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1138"},{"key":"ref38","article-title":"The neural noisy channel","volume-title":"ICLR 2017","author":"Yu","year":"2017"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2752691"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1212"},{"key":"ref41","article-title":"Sequence modeling and alignment for LVCSR-systems","volume-title":"ITG Conference on Speech Communication","author":"Beck"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-2020"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-2060"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W16-2206"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/w16-2206"},{"key":"ref46","article-title":"A study of latent monotonic attention variants","author":"Zeyer","year":"2021","journal-title":"Preprint"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1671"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004025"},{"key":"ref49","article-title":"A new training pipeline for an improved neural transducer","volume-title":"Interspeech","author":"Zeyer"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1705"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6322"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1992.225858"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p16-1162"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-4022"},{"key":"ref56","article-title":"Rasr - the rwth aachen university open source speech recognition toolkit","volume-title":"IEEE Automatic Speech Recognition and Understanding Workshop","author":"Rybach"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003788"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1255"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413648"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-211"}],"event":{"name":"2022 IEEE Spoken Language Technology Workshop (SLT)","location":"Doha, Qatar","start":{"date-parts":[[2023,1,9]]},"end":{"date-parts":[[2023,1,12]]}},"container-title":["2022 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10022052\/10022330\/10022818.pdf?arnumber=10022818","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T06:36:23Z","timestamp":1707806183000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10022818\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,9]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/slt54892.2023.10022818","relation":{},"subject":[],"published":{"date-parts":[[2023,1,9]]}}}