{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T15:17:15Z","timestamp":1780672635902,"version":"3.54.1"},"reference-count":60,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,1,19]]},"DOI":"10.1109\/slt48900.2021.9383515","type":"proceedings-article","created":{"date-parts":[[2021,3,25]],"date-time":"2021-03-25T20:46:54Z","timestamp":1616705214000},"page":"243-250","source":"Crossref","is-referenced-by-count":62,"title":["Internal Language Model Estimation for Domain-Adaptive End-to-End Speech Recognition"],"prefix":"10.1109","author":[{"given":"Zhong","family":"Meng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sarangarajan","family":"Parthasarathy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eric","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yashesh","family":"Gaur","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Naoyuki","family":"Kanda","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liang","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xie","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinyu","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yifan","family":"Gong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462682"},{"key":"ref38","article-title":"Towards better decoding and language model integration in sequence to sequence models","volume":"abs 1613 2695","author":"chorowski","year":"2016","journal-title":"CoRR"},{"key":"ref33","article-title":"Unsupervised adaptation with domain separation networks for robust speech recognition","author":"meng","year":"2017","journal-title":"Proc ASRU"},{"key":"ref32","article-title":"Invariant representations for noisy speech recognition","author":"serdyuk","year":"2016","journal-title":"NIPS Workshop"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461932"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-879"},{"key":"ref37","article-title":"On using monolingual corpora in neural machine translation","author":"gulcehre","year":"2015","journal-title":"CoRR"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003776"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3135"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462161"},{"key":"ref60","article-title":"A fast and simple algorithm for training neural probabilistic language models","author":"mnih","year":"2012"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639211"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178787"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2601146"},{"key":"ref2","first-page":"6059","article-title":"A streaming on-device end-to-end model surpassing server-side conventional model quality and latency","author":"sainath","year":"2020","journal-title":"Proc ICASSP"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053300"},{"key":"ref22","first-page":"1910","article-title":"Learning small-size DNN with output-distribution-based criteria","author":"li","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078569"},{"key":"ref24","first-page":"250","article-title":"A teacher-student learning approach for unsupervised domain adaptation of sequence-trained asr models","author":"manohar","year":"2018","journal-title":"Proc SLT"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461682"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2006.11.005"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683438"},{"key":"ref50","article-title":"Automatic differentiation in pytorch","author":"paszke","year":"2017"},{"key":"ref51","article-title":"Long short-term memory recurrent neural network architectures for large scale acoustic modeling","author":"beaufays","year":"2014","journal-title":"InterSpeech"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref58","first-page":"1171","article-title":"Scheduled sampling for sequence prediction with recurrent neural networks","author":"bengio","year":"2015","journal-title":"NeurIPS"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3056"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004018"},{"key":"ref55","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from over-fitting","volume":"15","author":"srivastava","year":"2014","journal-title":"The Journal of Machine Learning Research"},{"key":"ref54","article-title":"Layer normalization","author":"ba","year":"2016"},{"key":"ref53","first-page":"1","article-title":"Multi-channel speech recognition: Lstms all the way through","author":"erdogan","year":"2016","journal-title":"CHiME Workshop"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952160"},{"key":"ref10","article-title":"RNN-T for latency controlled asr with improved beam search","author":"jain","year":"2019"},{"key":"ref11","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"NIPS"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1392"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003750"},{"key":"ref15","article-title":"On the comparison of popular end-to-end models for large scale speech recognition","author":"li","year":"2020","journal-title":"Proc INTERSPEECH"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639201"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682510"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639212"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3016"},{"key":"ref6","article-title":"Deep speech: Scaling up end-to-end speech recognition","author":"hannun","year":"2014"},{"key":"ref5","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","author":"graves","year":"2014","journal-title":"International Conference on Machine Learning"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462017"},{"key":"ref7","article-title":"Neural speech recognizer: Acoustic-to-word lstm model for large vocabulary speech recognition","author":"soltau","year":"2016","journal-title":"Proc INTERSPEECH"},{"key":"ref49","article-title":"Neural machine translation of rare words with subword units","author":"sennrich","year":"2015"},{"key":"ref9","article-title":"Sequence transduction with recurrent neural networks","author":"graves","year":"2012"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268948"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-71"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053600"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2678162"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6321"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639038"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003790"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682490"}],"event":{"name":"2021 IEEE Spoken Language Technology Workshop (SLT)","location":"Shenzhen, China","start":{"date-parts":[[2021,1,19]]},"end":{"date-parts":[[2021,1,22]]}},"container-title":["2021 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9383468\/9383452\/09383515.pdf?arnumber=9383515","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,31]],"date-time":"2021-05-31T21:30:40Z","timestamp":1622496640000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9383515\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,19]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/slt48900.2021.9383515","relation":{},"subject":[],"published":{"date-parts":[[2021,1,19]]}}}