{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:28:38Z","timestamp":1753601318870,"version":"3.28.0"},"reference-count":35,"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\/asru51503.2021.9688101","type":"proceedings-article","created":{"date-parts":[[2022,2,3]],"date-time":"2022-02-03T15:31:00Z","timestamp":1643902260000},"page":"526-533","source":"Crossref","is-referenced-by-count":19,"title":["On Addressing Practical Challenges for RNN-Transducer"],"prefix":"10.1109","author":[{"given":"Rui","family":"Zhao","sequence":"first","affiliation":[{"name":"Microsoft Speech and Language Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Xue","sequence":"additional","affiliation":[{"name":"Microsoft Speech and Language Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinyu","family":"Li","sequence":"additional","affiliation":[{"name":"Microsoft Speech and Language Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenning","family":"Wei","sequence":"additional","affiliation":[{"name":"Microsoft Speech and Language Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"He","sequence":"additional","affiliation":[{"name":"Microsoft Speech and Language Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yifan","family":"Gong","sequence":"additional","affiliation":[{"name":"Microsoft Speech and Language Group"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","first-page":"7699","article-title":"High-accuracy and low-latency speech recognition with two-head con-textual layer trajectory LSTM model","author":"li","year":"0","journal-title":"Proc ICASSP"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-552"},{"journal-title":"Modeling multi-speaker latent space to improve neural TTS Quick en-rolling new speaker and enhancing premium voice","year":"2018","author":"deng","key":"ref31"},{"key":"ref30","first-page":"1-1149?1","article-title":"Random forests-based con-fidence annotation using novel features from confusion network","author":"xue","year":"0","journal-title":"Proc ICASSP"},{"key":"ref35","first-page":"7413","article-title":"Predicting speech recognition con-fidence using deep learning with word identity and score features","author":"huang","year":"0","journal-title":"Proc ICASSP"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462017"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053896"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003906"},{"key":"ref13","article-title":"Exploring neural transducers for end-to-end speech recognition","author":"battenberg","year":"0","journal-title":"Proc ASRU"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2846"},{"key":"ref16","article-title":"Transformer-transducer: End-to-end speech recognition with self-attention","author":"yeh","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref17","article-title":"Developing real-time streaming trans-former transducer for speech recognition on large-scale dataset","author":"chen","year":"0","journal-title":"ICASSP"},{"key":"ref18","article-title":"Adaptation al-gorithms for neural network-based speech recognition: An overview","volume":"2","author":"bell","year":"2021","journal-title":"Open Signal Process J"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053191"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413966"},{"key":"ref4","article-title":"Attention is all you need","author":"ashish","year":"0","journal-title":"Advances in neural information processing systems"},{"key":"ref27","first-page":"258","article-title":"An evaluation of word-level confidence estimation for end-to-end automatic speech recognition","author":"dan","year":"0","journal-title":"Proc SLT"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"1240","DOI":"10.1109\/JSTSP.2017.2763455","article-title":"Hybrid CTC\/attention architecture for end-to-end speech recognition","volume":"11","author":"shinji","year":"2017","journal-title":"IEEE Journal of Selected Topics in Signal Processing"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1006\/csla.2000.0152"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682336"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3016"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054188"},{"key":"ref2","article-title":"Sequence transduction with recurrent neural networks","author":"graves","year":"0","journal-title":"International Conference on Ma-chine Learning Representation Learning Workshop"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404790"},{"key":"ref1","first-page":"369","article-title":"Connectionist temporal classifi-cation: Labelling unsegmented sequence data with re-current neural networks","author":"graves","year":"0","journal-title":"ICML"},{"key":"ref20","article-title":"Improving performance of end-to-end ASR on numeric sequences","author":"cal","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1555"},{"key":"ref21","article-title":"Self-supervised sequence-to-sequence ASR using un-paired speech and text","author":"baskar","year":"0","journal-title":"Conference of the International Speech Communication Association"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639506"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003776"},{"key":"ref26","article-title":"FastEmit: Low-latency Streaming ASR with Sequence-level Emission Regularization","author":"jiahui","year":"0","journal-title":"ICASSP"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1059"}],"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\/09688101.pdf?arnumber=9688101","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,16]],"date-time":"2022-05-16T16:42:23Z","timestamp":1652719343000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9688101\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,13]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/asru51503.2021.9688101","relation":{},"subject":[],"published":{"date-parts":[[2021,12,13]]}}}