{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,18]],"date-time":"2025-01-18T05:07:55Z","timestamp":1737176875850,"version":"3.33.0"},"reference-count":42,"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"}],"funder":[{"DOI":"10.13039\/501100000735","name":"University of Cambridge","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000735","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,12,2]]},"DOI":"10.1109\/slt61566.2024.10832353","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:27Z","timestamp":1737052287000},"page":"132-139","source":"Crossref","is-referenced-by-count":0,"title":["Automatic Time Alignment Generation For End-to-End ASR Using Acoustic Probability Modelling"],"prefix":"10.1109","author":[{"given":"Dongcheng","family":"Jiang","sequence":"first","affiliation":[{"name":"University of Cambridge, Trumpington St.,Department of Engineering,Cambridge,UK,CB2 1PZ"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Electrical Engineering,Beijing,P. R. China,100084"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Philip C.","family":"Woodland","sequence":"additional","affiliation":[{"name":"University of Cambridge, Trumpington St.,Department of Engineering,Cambridge,UK,CB2 1PZ"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"article-title":"Sequence transduction with recurrent neural networks","volume-title":"Proc. ICML Workshop on Representation Learning","author":"Graves","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054250"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022774"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1059"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.35111\/17gk-bn40"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60276-5_27"},{"article-title":"NeMo forced aligner and its application to word alignment for subtitle generation","volume-title":"Proc. Interspeech","author":"Rastorgueva","key":"ref13"},{"key":"ref14","article-title":"A toolbox for construction and analysis of speech datasets","volume-title":"Proceedings NeurIPS Track on Datasets and Benchmarks","volume":"1","author":"Bakhturina"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1071"},{"author":"Louradour","key":"ref16","article-title":"Whisper-timestamped"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022818"},{"article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. ICML","author":"Radford","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-78"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-2401-1_8"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3161159"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-894"},{"article-title":"On addressing practical challenges for RNNtransducer","volume-title":"Proc. ASRU","author":"Zhao","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3133217"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389749"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688056"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747085"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3190793"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053600"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-561"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2198"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1073"},{"article-title":"Why does CTC result in peaky behavior?","volume-title":"arXiv preprint 2105.14849","author":"Zeyer","key":"ref33"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2396"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1386"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1456"},{"article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. ICLR","author":"Kingma","key":"ref37"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414212"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-293"}],"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\/10832353.pdf?arnumber=10832353","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T08:11:30Z","timestamp":1737101490000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10832353\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/slt61566.2024.10832353","relation":{},"subject":[],"published":{"date-parts":[[2024,12,2]]}}}