{"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":1780672635111,"version":"3.54.1"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10096429","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":16,"title":["Large-Scale Language Model Rescoring on Long-Form Data"],"prefix":"10.1109","author":[{"given":"Tongzhou","family":"Chen","sequence":"first","affiliation":[{"name":"Google LLC,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cyril","family":"Allauzen","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yinghui","family":"Huang","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel","family":"Park","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Rybach","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"W. Ronny","family":"Huang","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rodrigo","family":"Cabrera","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kartik","family":"Audhkhasi","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bhuvana","family":"Ramabhadran","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pedro J.","family":"Moreno","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Riley","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1465"},{"key":"ref35","article-title":"Scaling laws for neural language models","author":"kaplan","year":"2020"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639693"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414212"},{"key":"ref15","article-title":"On using monolingual corpora in neural machine translation","author":"gulcehre","year":"2015"},{"key":"ref37","article-title":"Improving accuracy of rare words for rnn-transducer through unigram shallow fusion","author":"ravi","year":"2020"},{"key":"ref14","article-title":"Cold fusion: Training seq2seq models together with language models","author":"sriram","year":"2017"},{"key":"ref36","article-title":"Training compute-optimal large language models","author":"hoffmann","year":"2022"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1203"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-566"},{"key":"ref11","article-title":"Towards better decoding and language model integration in sequence to sequence models","author":"chorowski","year":"2016"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-268"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854829"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003822"},{"key":"ref2","article-title":"Bert has a mouth, and it must speak: Bert as a markov random field language model","author":"wang","year":"2019"},{"key":"ref1","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"raffel","year":"2020","journal-title":"J Mach Learn Res"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462682"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682490"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003790"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053600"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.41"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003913"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707758"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-658"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-243"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-206"},{"key":"ref28","article-title":"Ccnet: Extracting high quality monolingual datasets from web crawl data","author":"wenzek","year":"2019"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639699"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-212"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054745"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.240"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383557"},{"key":"ref4","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref3","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"raffel","year":"2020","journal-title":"Journal of Machine Learning Research"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688232"},{"key":"ref5","article-title":"Palm: Scaling language modeling with pathways","author":"chowdhery","year":"2022"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10096429.pdf?arnumber=10096429","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T18:59:41Z","timestamp":1699901981000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096429\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096429","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}