{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T12:17:27Z","timestamp":1767183447591},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"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":[[2023,12,16]]},"DOI":"10.1109\/asru57964.2023.10389653","type":"proceedings-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T18:38:40Z","timestamp":1705689520000},"page":"1-6","source":"Crossref","is-referenced-by-count":1,"title":["Multi Transcription-Style Speech Transcription Using Attention-Based Encoder-Decoder Model"],"prefix":"10.1109","author":[{"given":"Yan","family":"Huang","sequence":"first","affiliation":[{"name":"Microsoft Corporation"}]},{"given":"Piyush","family":"Behre","sequence":"additional","affiliation":[{"name":"Microsoft Corporation"}]},{"given":"Guoli","family":"Ye","sequence":"additional","affiliation":[{"name":"Microsoft Corporation"}]},{"given":"Shawn","family":"Chang","sequence":"additional","affiliation":[{"name":"Microsoft Corporation"}]},{"given":"Yifan","family":"Gong","sequence":"additional","affiliation":[{"name":"Microsoft Corporation"}]}],"member":"263","reference":[{"article-title":"The English writing system: Notes towards a description, journal schools council program in linguistics and english teaching papers series 2","year":"1972","author":"Albrow","key":"ref1"},{"article-title":"Modeling punctuation prediction as machine translation","volume-title":"Proceedings of the International Workshop on Spoken Language Translation (IWSL)","author":"Peitz","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1571"},{"article-title":"RNN approaches to text normalization: A challenge","volume-title":"Proceedings of the International Workshop on Spoken Language Translation (IWSL)","author":"Sproat","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1274"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023257"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.5121\/ijnlc.2022.11601"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.878255"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414912"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3557894"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(00)00028-5"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-1566"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2017.7953075"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268935"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682336"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003906"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053606"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1561\/116.00000050"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1860"},{"article-title":"Robust speech recognition via large-scale weak supervision","year":"2022","author":"Radford","key":"ref21"},{"article-title":"ESB: A benchmark for multi-domain end-to-end speech recognition","year":"2022","author":"Kang","key":"ref22"},{"article-title":"LIBRIHEAVY: A 50,000 hours ASR corpus with punctuation casing and context","year":"2023","author":"Gandhi","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639081"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-497"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.661"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00340"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.216"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1981"},{"key":"ref30","article-title":"Endto-end continuous speech recognition using attention-based recurrent NN: First results","author":"Chorowski","year":"2014","journal-title":"arXiv preprint arXiv:1412.1602"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2017.7953075"}],"event":{"name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","start":{"date-parts":[[2023,12,16]]},"location":"Taipei, Taiwan","end":{"date-parts":[[2023,12,20]]}},"container-title":["2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10388490\/10389614\/10389653.pdf?arnumber=10389653","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T16:58:21Z","timestamp":1706029101000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10389653\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,16]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/asru57964.2023.10389653","relation":{},"subject":[],"published":{"date-parts":[[2023,12,16]]}}}