{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T10:04:17Z","timestamp":1767261857777},"reference-count":48,"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\/icassp39728.2021.9413562","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T15:53:45Z","timestamp":1620921225000},"page":"5859-5863","source":"Crossref","is-referenced-by-count":28,"title":["Transformer-Transducers for Code-Switched Speech Recognition"],"prefix":"10.1109","author":[{"given":"Siddharth","family":"Dalmia","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuzong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Srikanth","family":"Ronanki","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Katrin","family":"Kirchhoff","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1343"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6289015"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1959"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947480"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683223"},{"key":"ref37","article-title":"Enhancing the TED-LIUM Corpus with Selected Data for Language Modeling and More TED Talks","author":"rousseau","year":"2014","journal-title":"Proc LREC"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2017.8384449"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref34","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2010-563","article-title":"SEAME: a Mandarin-English code-switching speech corpus in south-east asia","author":"lyu","year":"2010","journal-title":"Proc INTERSPEECH"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639674"},{"key":"ref11","article-title":"Sequence Transduction with Recurrent Neural Networks","author":"graves","year":"2012","journal-title":"ICML Representation Learning Worksop"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1867"},{"article-title":"RNN-Transducer with language bias for end-to-end Mandarin-English code-switching speech recognition","year":"2020","author":"zhang","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2488"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1855"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053896"},{"key":"ref28","article-title":"Data Noising as Smoothing in Neural Network Language Models","author":"xie","year":"2017","journal-title":"ICLRE"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707719"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1429"},{"article-title":"A Survey of Code-switched Speech and Language Processing","year":"2019","author":"sitaram","key":"ref3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639655"},{"key":"ref29","article-title":"A Theoretically Grounded Application of Dropout in Recurrent Neural Networks","author":"gal","year":"2016","journal-title":"Proc NeurIPS"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2016.04.024"},{"key":"ref8","article-title":"Combination of Recurrent Neural Networks and Factored Language Models for Code-Switching Language Modeling","author":"adel","year":"2013","journal-title":"Proc ACL"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461802"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1075\/impact.1.25muy"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-3202"},{"year":"0","key":"ref1","article-title":"Multilingual People"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2361"},{"article-title":"Transformer-Transducer: End-to-End Speech Recognition with Self-Attention","year":"2019","author":"yeh","key":"ref20"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003906"},{"article-title":"Enforcing encoder-decoder modularity in sequence-to-sequence models","year":"2019","author":"dalmia","key":"ref48"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462506"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-233"},{"key":"ref21","article-title":"Attention is All you Need","author":"vaswani","year":"2017","journal-title":"Proc NeurIPS"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682478"},{"key":"ref24","article-title":"The Kaldi Speech Recognition Toolkit","author":"povey","year":"2011","journal-title":"Proc ASRU"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639699"},{"key":"ref23","article-title":"Exploring neural transducers for end-to-end speech recognition","author":"battenberg","year":"2017","journal-title":"Proc ASRU"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682336"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054663"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682850"},{"article-title":"Multilingual training and cross-lingual adaptation on CTC-based acoustic model","year":"2017","author":"tong","key":"ref25"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2021,6,6]]},"location":"Toronto, ON, Canada","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\/09413562.pdf?arnumber=9413562","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,27]],"date-time":"2022-12-27T03:24:03Z","timestamp":1672111443000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9413562\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9413562","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}