{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:29:05Z","timestamp":1775230145157,"version":"3.50.1"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9053600","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"6139-6143","source":"Crossref","is-referenced-by-count":88,"title":["Hybrid Autoregressive Transducer (HAT)"],"prefix":"10.1109","author":[{"given":"Ehsan","family":"Variani","sequence":"first","affiliation":[]},{"given":"David","family":"Rybach","sequence":"additional","affiliation":[]},{"given":"Cyril","family":"Allauzen","sequence":"additional","affiliation":[]},{"given":"Michael","family":"Riley","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref32","article-title":"Sequence level training with recurrent neural networks","author":"ranzato","year":"2015"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682336"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1203"},{"key":"ref10","article-title":"Discriminative training on language model","author":"chen","year":"2000","journal-title":"Sixth International Conference on Spoken Language Processing"},{"key":"ref11","author":"auli","year":"2013","journal-title":"Joint language and translation modeling with recurrent neural networks"},{"key":"ref12","first-page":"1700","article-title":"Recurrent continuous translation models","author":"kalchbrenner","year":"2013","journal-title":"Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2009.5373257"},{"key":"ref16","article-title":"Neural speech recognizer: Acoustic-to-word lstm model for large vocabulary speech recognition","author":"soltau","year":"2016"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1683"},{"key":"ref18","article-title":"Sequence transduction with recurrent neural networks","author":"graves","year":"2012"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref28","author":"variani","year":"2017","journal-title":"End-to-end training of acoustic models for large vocabulary continuous speech recognition with tensorflow"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-49127-9_28"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1214\/ss\/1177013621"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1006\/csla.2001.0184"},{"key":"ref6","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2015-340","article-title":"Composition-based on-the-fly rescoring for salient n-gram biasing","author":"hall","year":"2015","journal-title":"Interspeech 2015 International Speech Communications Association"},{"key":"ref29","article-title":"Efficient implementation of the room simulator for training deep neural network acoustic models","author":"kim","year":"2017"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2015-477","article-title":"Rapid vocabulary addition to context-dependent decoder graphs","author":"allauzen","year":"2015","journal-title":"Proceedings of Interspeech 2015"},{"key":"ref8","article-title":"Discriminative training for large vocabulary speech recognition","author":"povey","year":"2005","journal-title":"Ph D thesis"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1986.1169179"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.1983.4767370"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1976.10159"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960445"},{"key":"ref20","article-title":"On using monolingual corpora in neural machine translation","author":"gulcehre","year":"2015"},{"key":"ref22","first-page":"1","article-title":"An analysis of incorporating an external language model into a sequence-to-sequence model","author":"kannan","year":"2018","journal-title":"2018 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref21","article-title":"Towards better decoding and language model integration in sequence to sequence models","author":"chorowski","year":"2016"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-04221-9_19"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462380"},{"key":"ref26","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2015-350","article-title":"Fast and accurate recurrent neural network acoustic models for speech recognition","author":"sak","year":"2015"},{"key":"ref25","article-title":"Model unit exploration for sequence-to-sequence speech recognition","author":"irie","year":"2019"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Barcelona, Spain","start":{"date-parts":[[2020,5,4]]},"end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09053600.pdf?arnumber=9053600","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,29]],"date-time":"2023-09-29T19:29:22Z","timestamp":1696015762000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9053600\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9053600","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}