{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:24:35Z","timestamp":1775229875189,"version":"3.50.1"},"reference-count":63,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,1,9]]},"DOI":"10.1109\/slt54892.2023.10023194","type":"proceedings-article","created":{"date-parts":[[2023,1,27]],"date-time":"2023-01-27T18:54:03Z","timestamp":1674845643000},"page":"197-204","source":"Crossref","is-referenced-by-count":12,"title":["Modular Hybrid Autoregressive Transducer"],"prefix":"10.1109","author":[{"given":"Zhong","family":"Meng","sequence":"first","affiliation":[{"name":"Google LLC.,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tongzhou","family":"Chen","sequence":"additional","affiliation":[{"name":"Google LLC.,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rohit","family":"Prabhavalkar","sequence":"additional","affiliation":[{"name":"Google LLC.,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Google LLC.,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gary","family":"Wang","sequence":"additional","affiliation":[{"name":"Google LLC.,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kartik","family":"Audhkhasi","sequence":"additional","affiliation":[{"name":"Google LLC.,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jesse","family":"Emond","sequence":"additional","affiliation":[{"name":"Google LLC.,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Trevor","family":"Strohman","sequence":"additional","affiliation":[{"name":"Google LLC.,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bhuvana","family":"Ramabhadran","sequence":"additional","affiliation":[{"name":"Google LLC.,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"W. Ronny","family":"Huang","sequence":"additional","affiliation":[{"name":"Google LLC.,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ehsan","family":"Variani","sequence":"additional","affiliation":[{"name":"Google LLC.,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yinghui","family":"Huang","sequence":"additional","affiliation":[{"name":"Google LLC.,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pedro J.","family":"Moreno","sequence":"additional","affiliation":[{"name":"Google LLC.,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref2","article-title":"Deep speech: Scaling up end-to-end speech recognition","author":"Hannun","year":"2014","journal-title":"arXiv preprint"},{"key":"ref3","article-title":"Sequence transduction with recurrent neural net-works","author":"Graves","year":"2012","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"RNN-T for la-tency controlled ASR with improved beam search","author":"Jain","year":"2019","journal-title":"ar Xiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054188"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3016"},{"key":"ref7","article-title":"Attention-based models for speech recognition","author":"Chorowski","year":"2015","journal-title":"NIPS"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2018.8462105"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639201"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682510"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639212"},{"key":"ref13","article-title":"L-vector: Neural label embed-ding for domain adaptation","volume-title":"Proc. ICASSP","author":"Meng","year":"2020"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/slt.2014.7078569"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2014-432"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461682"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639635"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683438"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2006.11.005"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178787"},{"key":"ref21","article-title":"Fast speaker adaptation of hy-brid nn\/hmm model for speech recognition based on discrimi-native learning of speaker code","volume-title":"Proc. ICASSP","author":"Abdel-Hamid","year":"2013"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-879"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461932"},{"key":"ref24","article-title":"Invariant representations for noisy speech recognition","volume-title":"NIPS Workshop","author":"Serdyuk","year":"2016"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/asru.2017.8268938"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2018.8462161"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3135"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003776"},{"key":"ref29","article-title":"On using monolingual corpora in neural machine translation","author":"Gulcehre","year":"2015","journal-title":"CaRR"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003790"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-71"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178776"},{"key":"ref33","article-title":"Hybrid autore-gressive transducer (hat)","author":"Variani","year":"2020","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383515"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1510"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1345"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1290"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1475"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1191"},{"key":"ref40","article-title":"Internal language model adaptation with text-only data for end-to-end speech recognition","author":"Meng","year":"2021","journal-title":"arXiv preprint"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415039"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746908"},{"key":"ref43","article-title":"A new training pipeline for an improved neural trans-ducer","author":"Zeyer","year":"2020","journal-title":"arXiv preprint"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729694"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref46","article-title":"Ted-lium: an auto-matic speech recognition dedicated corpus","author":"Rousseau","year":"2012","journal-title":"LREC"},{"key":"ref47","article-title":"Common voice: A massively-multilingual speech corpus","author":"Ardila","year":"2019","journal-title":"arXiv preprint"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-99579-3_21"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-212"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6289079"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-80"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2017.7952160"},{"key":"ref54","first-page":"1","article-title":"Multi-channel speech recog-nition: LSTMs all the way through","volume-title":"CHiME-4 workshop","author":"Erdogan","year":"2016"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747879"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003913"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/asru.2013.6707758"},{"key":"ref58","volume-title":"Artificial intelligence at google: Our principles.","year":"2022"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-1510"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/slt.2012.6424210"},{"key":"ref61","article-title":"Specaugment: A simple data augmentation method for automatic speech recognition","author":"SPark","year":"2019","journal-title":"arXiv preprint"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1341"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414607"}],"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\/10023194.pdf?arnumber=10023194","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T06:44:54Z","timestamp":1707806694000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10023194\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,9]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/slt54892.2023.10023194","relation":{},"subject":[],"published":{"date-parts":[[2023,1,9]]}}}