{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T10:55:27Z","timestamp":1730199327751,"version":"3.28.0"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"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":[[2021,12,13]]},"DOI":"10.1109\/asru51503.2021.9687943","type":"proceedings-article","created":{"date-parts":[[2022,2,3]],"date-time":"2022-02-03T20:31:00Z","timestamp":1643920260000},"page":"395-402","source":"Crossref","is-referenced-by-count":0,"title":["HiTNet: Byte-to-BPE Hierarchical Transcription Network for End-to-End Speech Recognition"],"prefix":"10.1109","author":[{"given":"Dhananjaya","family":"Gowda","sequence":"first","affiliation":[{"name":"Samsung Research,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abhinav","family":"Garg","sequence":"additional","affiliation":[{"name":"Samsung Research,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiyeon","family":"Kim","sequence":"additional","affiliation":[{"name":"Samsung Research,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mehul","family":"Kumar","sequence":"additional","affiliation":[{"name":"Samsung Research,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sachin","family":"Singh","sequence":"additional","affiliation":[{"name":"Samsung Research,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ashutosh","family":"Gupta","sequence":"additional","affiliation":[{"name":"Samsung Research,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ankur","family":"Kumar","sequence":"additional","affiliation":[{"name":"Samsung Research,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nauman","family":"Dawalatabad","sequence":"additional","affiliation":[{"name":"Samsung Research,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aman","family":"Maghan","sequence":"additional","affiliation":[{"name":"Samsung Research,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shatrughan","family":"Singh","sequence":"additional","affiliation":[{"name":"Samsung Research,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chanwoo","family":"Kim","sequence":"additional","affiliation":[{"name":"Samsung Research,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref33","DOI":"10.1007\/978-3-030-30493-5_39"},{"doi-asserted-by":"publisher","key":"ref32","DOI":"10.1109\/ICASSP.2019.8682674"},{"doi-asserted-by":"publisher","key":"ref31","DOI":"10.1109\/ICASSP.2015.7178964"},{"doi-asserted-by":"publisher","key":"ref30","DOI":"10.1109\/ICASSP.2019.8682903"},{"doi-asserted-by":"publisher","key":"ref34","DOI":"10.18653\/v1\/N16-1174"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1109\/ICASSP40776.2020.9053606"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1109\/ASRU46091.2019.9004027"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.21437\/Interspeech.2019-3227"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1109\/IEEECONF51394.2020.9443456"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1109\/ICASSP39728.2021.9414117"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.21437\/Interspeech.2020-3172"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1109\/ASRU46091.2019.9003976"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.21437\/Interspeech.2020-3216"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1109\/ICASSP39728.2021.9414467"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.21437\/Interspeech.2020-3174"},{"doi-asserted-by":"publisher","key":"ref28","DOI":"10.21437\/Interspeech.2020-3230"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref27","article-title":"Multi-task multi-resolution char-to-bpe cross-attention decoder for end-to-end speech recognition","author":"abhinav","year":"2019","journal-title":"InterSpeech"},{"key":"ref3","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"0","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1109\/ICASSP.2018.8462366"},{"doi-asserted-by":"publisher","key":"ref29","DOI":"10.21437\/Interspeech.2019-1341"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref8","article-title":"Optimal completion distillation for sequence learning","volume":"abs 1810 1398","author":"sabour","year":"2018","journal-title":"CoRR"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.21437\/Interspeech.2018-1616"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1109\/ASRU.2017.8268935"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.21437\/Interspeech.2019-2680"},{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1145\/1143844.1143891"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1145\/1553374.1553380"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1109\/ICASSP.2018.8461361"},{"key":"ref21","first-page":"485","article-title":"Hierarchical multitask learning with etc","author":"sanabria","year":"0","journal-title":"2018 IEEE Spoken Language Technology Workshop (SLT)"},{"doi-asserted-by":"publisher","key":"ref24","DOI":"10.1109\/ICASSP.2017.7953071"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1109\/ASRU46091.2019.9003936"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.21437\/Interspeech.2018-1452"},{"key":"ref25","first-page":"193","article-title":"Exploring architectures, data and units for streaming end-to-end speech recognition with rnn-transducer","author":"rao","year":"0","journal-title":"Automatic Speech Recognition and Understanding (ASRU) 2017 IEEE Workshop on"}],"event":{"name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","start":{"date-parts":[[2021,12,13]]},"location":"Cartagena, Colombia","end":{"date-parts":[[2021,12,17]]}},"container-title":["2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9687821\/9687855\/09687943.pdf?arnumber=9687943","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,16]],"date-time":"2022-05-16T20:42:08Z","timestamp":1652733728000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9687943\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,13]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/asru51503.2021.9687943","relation":{},"subject":[],"published":{"date-parts":[[2021,12,13]]}}}