{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T18:21:42Z","timestamp":1775845302209,"version":"3.50.1"},"reference-count":26,"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\/icassp40776.2020.9053896","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"7829-7833","source":"Crossref","is-referenced-by-count":293,"title":["Transformer Transducer: A Streamable Speech Recognition Model with Transformer Encoders and RNN-T Loss"],"prefix":"10.1109","author":[{"given":"Qian","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Han","family":"Lu","sequence":"additional","affiliation":[]},{"given":"Hasim","family":"Sak","sequence":"additional","affiliation":[]},{"given":"Anshuman","family":"Tripathi","sequence":"additional","affiliation":[]},{"given":"Erik","family":"McDermott","sequence":"additional","affiliation":[]},{"given":"Stephen","family":"Koo","sequence":"additional","affiliation":[]},{"given":"Shankar","family":"Kumar","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682954"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1910"},{"key":"ref12","article-title":"Towards online end-to-end transformer automatic speech recognition","author":"tsunoo","year":"2019"},{"key":"ref13","article-title":"Long Short-Term Memory Recurrent Neural Network Architectures for Large Scale Acoustic Modeling","author":"sak","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref14","article-title":"Sequence transduction with recurrent neural networks","author":"graves","year":"2012","journal-title":"Proceedings of the 29th International Conference on Machine Learning"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268935"},{"key":"ref16","doi-asserted-by":"crossref","DOI":"10.1109\/ASRU.2017.8268974","article-title":"Streaming small-footprint keyword spotting using sequence-to-sequence models","author":"he","year":"2017","journal-title":"Automatic Speech Recognition and Understanding (ASRU) 2017 IEEE Workshop on"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1705"},{"key":"ref18","article-title":"A neural transducer","author":"jaitly","year":"2015"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref4","first-page":"5884","article-title":"Speech-transformer: A no-recurrence sequence-to-sequence model for speech recognition","author":"dong","year":"2018","journal-title":"Proc ICASSP"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2225"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1176"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2702"},{"key":"ref8","article-title":"Transformers with convolutional context for ASR","author":"mohamed","year":"2019","journal-title":"CoRR"},{"key":"ref7","first-page":"791","article-title":"Syllable-based sequence-to-sequence speech recognition with the transformer in mandarin chinese","year":"0","journal-title":"Interspeech 2018"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462497"},{"key":"ref1","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003822"},{"key":"ref22","article-title":"Transformer-based acoustic modeling for hybrid speech recognition","author":"wang","year":"2019"},{"key":"ref21","author":"rabiner","year":"1993","journal-title":"Fundamentals of speech recognition"},{"key":"ref24","first-page":"5206","article-title":"Librispeech: an asr corpus based on public domain audio books","author":"panayotov","year":"2015","journal-title":"Proc ICASSP"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"523","DOI":"10.21437\/Interspeech.2017-343","article-title":"Towards better decoding and language model integration in sequence to sequence models","author":"chorowski","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref25","first-page":"2348","article-title":"Practical variational inference for neural networks","author":"graves","year":"2011","journal-title":"Advances in neural information processing systems"}],"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\/09053896.pdf?arnumber=9053896","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:28:06Z","timestamp":1656376086000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9053896\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9053896","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}