{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:29:05Z","timestamp":1775230145938,"version":"3.50.1"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"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":[[2019,12]]},"DOI":"10.1109\/asru46091.2019.9003790","type":"proceedings-article","created":{"date-parts":[[2020,2,21]],"date-time":"2020-02-21T07:01:33Z","timestamp":1582268493000},"page":"434-441","source":"Crossref","is-referenced-by-count":66,"title":["A Density Ratio Approach to Language Model Fusion in End-to-End Automatic Speech Recognition"],"prefix":"10.1109","author":[{"given":"Erik","family":"McDermott","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hasim","family":"Sak","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ehsan","family":"Variani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref31","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"International Conference on Learning Representations ICLR 2015"},{"key":"ref30","article-title":"Morfessor 2.0: Python implementation and extensions for morfessor baseline","author":"virpioja","year":"2013","journal-title":"D4 julka-istu kehittmistai tutkimusraportti tai -selvitys"},{"key":"ref10","article-title":"On using monolingual corpora in neural machine translation","volume":"abs 1503 3535","author":"gulcehre","year":"2015","journal-title":"CoRR"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1392"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682490"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1976.10159"},{"key":"ref14","first-page":"1345","article-title":"On the Robustness of HMM and ANN Speech Recognition Algorithms","volume":"2","author":"minami","year":"1990","journal-title":"Proc International Conference on Spoken Language Processing"},{"key":"ref15","article-title":"Connectionist speech recognition with a global MMI algorithm","author":"haffner","year":"0","journal-title":"Proc Eurospeech 1993 ISCA"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960445"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163899"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref28","first-page":"368","article-title":"Large scale deep neural network acoustic modeling with semi -supervised training data for youtube video transcription","author":"hank","year":"2013","journal-title":"2013 IEEE Workshop on Automatic Speech Recognition and Understanding"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref27","volume":"7632","author":"rabiner","year":"1993","journal-title":"Fundamentals of speech recognition"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461935"},{"key":"ref6","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 2017"},{"key":"ref29","article-title":"Neu-ral speech recognizer: Acoustic-to-word LSTM model for large vocabulary speech recognition","volume":"abs 1610 9975","author":"soltau","year":"2016","journal-title":"CoRR"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2010-343","article-title":"Recurrent neural network based language model","author":"mikolov","year":"2010","journal-title":"InterSpeech"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462682"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268948"},{"key":"ref2","article-title":"Sequence transduction with recurrent neural networks","volume":"abs 1211 3711","author":"graves","year":"2012","journal-title":"CoRR"},{"key":"ref9","article-title":"A comparison of techniques for language model integration in encoder-decoder speech recognition","author":"toshniwal","year":"2018","journal-title":"CoRR"},{"key":"ref1","article-title":"Listen, attend and spell: A neural network for large vocabulary conversational speech recognition","author":"william","year":"2016","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref20","article-title":"Sequence discriminative distributed training of long short-term memory recurrent neural networks","author":"sak","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref22","article-title":"End-to-end training of acoustic models for large vocabulary continuous speech recognition with tensorflow","author":"variani","year":"2018","journal-title":"Proc INTERSPEECH"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-3210-1"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683713"},{"key":"ref26","article-title":"A deep generative acoustic model for compositional automatic speech recognition","author":"mcdermott","year":"2018","journal-title":"Proceedings of Neural Information Processing Systems (NeurIPS) Workshop Interpretability and Robustness in Audio Speech and Language"},{"key":"ref25","article-title":"End-to-end speech recognition with word-based RNN language models","volume":"abs 1808 2608","author":"hori","year":"2018","journal-title":"CoRR"}],"event":{"name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"SG, Singapore","start":{"date-parts":[[2019,12,14]]},"end":{"date-parts":[[2019,12,18]]}},"container-title":["2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8985378\/9003727\/09003790.pdf?arnumber=9003790","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,16]],"date-time":"2022-10-16T05:02:24Z","timestamp":1665896544000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9003790\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/asru46091.2019.9003790","relation":{},"subject":[],"published":{"date-parts":[[2019,12]]}}}