{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T18:25:02Z","timestamp":1780511102683,"version":"3.54.1"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"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":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9414716","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"5654-5658","source":"Crossref","is-referenced-by-count":66,"title":["Advancing RNN Transducer Technology for Speech Recognition"],"prefix":"10.1109","author":[{"given":"George","family":"Saon","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zoltan","family":"Tuske","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel","family":"Bolanos","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Brian","family":"Kingsbury","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1488"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1423"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003788"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1117\/12.2520589"},{"key":"ref36","article-title":"Minimum Bayes risk training of RNN-Transducer for end-to-end speech recognition","author":"weng","year":"2019"},{"key":"ref35","article-title":"Transformer-transducer: End-to-end speech recognition with self-attention","author":"yeh","year":"2019"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2442"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003906"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003822"},{"key":"ref12","article-title":"RNN-T for latency controlled ASR with improved beam search","author":"jain","year":"2019"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003790"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053600"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1855"},{"key":"ref16","article-title":"RNN-T models fail to generalize to out-of-domain audio: Causes and solutions","author":"chiu","year":"2020"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053040"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref19","article-title":"Audio augmentation for speech recognition","author":"ko","year":"2015","journal-title":"Sixteenth Annual Conference of the International Speech Communication Association"},{"key":"ref28","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"IEEE Workshop on Automatic Speech Recognition and Understanding"},{"key":"ref4","article-title":"Google’s neural machine translation system: Bridging the gap between human and machine translation","author":"wu","year":"2016"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707705"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1109\/ASRU.2017.8268935","article-title":"Exploring architectures, data and units for streaming end-to-end speech recognition with RNN-transducer","author":"rao","year":"2017","journal-title":"IEEE Autom Speech Recognition Understanding Workshop (ASRU)"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2841"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref8","article-title":"Exploring RNN-Transducer for Chinese speech recognition","author":"wang","year":"2018"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"206","DOI":"10.1109\/ASRU.2017.8268937","article-title":"Exploring neural transducers for end-to-end speech recognition","author":"battenberg","year":"2017","journal-title":"IEEE Autom Speech Recognition Understanding Workshop (ASRU)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682336"},{"key":"ref1","article-title":"Sequence transduction with recurrent neural networks","author":"graves","year":"2012"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683706"},{"key":"ref22","first-page":"1058","article-title":"Regularization of neural networks using DropConnect","author":"wan","year":"2013","journal-title":"International Conference on Machine Learning"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639690"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1100"},{"key":"ref26","article-title":"Multiplicative interactions and where to find them","author":"jayakumar","year":"2019","journal-title":"International Conference on Learning Representations"},{"key":"ref25","first-page":"2856","article-title":"On multiplicative integration with recurrent neural networks","author":"wu","year":"2016","journal-title":"Advances in neural information processing systems"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Toronto, ON, Canada","start":{"date-parts":[[2021,6,6]]},"end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09414716.pdf?arnumber=9414716","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:40:54Z","timestamp":1652197254000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414716\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414716","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}