{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T03:34:28Z","timestamp":1777952068738,"version":"3.51.4"},"reference-count":18,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T00:00:00Z","timestamp":1769731200000},"content-version":"vor","delay-in-days":29,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Procedia Computer Science"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1016\/j.procs.2026.01.037","type":"journal-article","created":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T19:30:19Z","timestamp":1774035019000},"page":"301-308","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Confidence Gated Fusion: Dynamic Language Model Integration for Adapting Pretrained Multilingual ASR Models with Text-Only Data"],"prefix":"10.1016","volume":"275","author":[{"given":"Nader","family":"Essam","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wael","family":"Ali","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Khaled","family":"Wassif","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sherif Mahdy","family":"Abdou Essawy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanaa","family":"Mobarz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.procs.2026.01.037_bib1","series-title":"Robust speech recognition via large-scale weak supervision, in:International conference on machine learning","first-page":"28492","author":"Radford","year":"2023"},{"key":"10.1016\/j.procs.2026.01.037_bib2","series-title":"Speech recognition challenge in the wild: Arabic mgb-3, in: 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","first-page":"316","author":"Ali","year":"2017"},{"key":"10.1016\/j.procs.2026.01.037_bib3","doi-asserted-by":"crossref","first-page":"10617","DOI":"10.1007\/s13369-023-07670-7","article-title":"End-to-end speech recognition for arabic dialects","volume":"48","author":"Nasr","year":"2023","journal-title":"Arabian Journal for Science and Engineering"},{"key":"10.1016\/j.procs.2026.01.037_bib4","doi-asserted-by":"crossref","unstructured":"M. Zeineldeen, A. Glushko, W. Michel, A. Zeyer, R. Schl\u00fcter, H. Ney, Investigating methods to improve language model integration for attention-based encoder-decoder asr models, arXiv preprint arXiv:2104.05544 (2021).","DOI":"10.21437\/Interspeech.2021-1255"},{"key":"10.1016\/j.procs.2026.01.037_bib5","series-title":"A comparison of techniques for language model integration in encoder-decoder speech recognition, in: 2018 IEEE spoken language technology workshop (SLT)","first-page":"369","author":"Toshniwal","year":"2018"},{"key":"10.1016\/j.procs.2026.01.037_bib6","unstructured":"V. Ravi, Y. Gu, A. Gandhe, A. Rastrow, L. Liu, D. Filimonov, S. Novotney, I. Bulyko, Improving accuracy of rare words for rnn-transducer through unigram shallow fusion, arXiv preprint arXiv:2012.00133 (2020)."},{"key":"10.1016\/j.procs.2026.01.037_bib7","unstructured":"A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, \u0141. Kaiser, I. Polosukhin, Attention is all you need, Advances in neural information processing systems 30 (2017)."},{"key":"10.1016\/j.procs.2026.01.037_bib8","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":"Watanabe","year":"2017","journal-title":"IEEE Journal of Selected Topics in Signal Processing"},{"key":"10.1016\/j.procs.2026.01.037_bib9","doi-asserted-by":"crossref","first-page":"325","DOI":"10.1109\/TASLP.2023.3328283","article-title":"End-to-end speech recognition: A survey","volume":"32","author":"Prabhavalkar","year":"2023","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"key":"10.1016\/j.procs.2026.01.037_bib10","doi-asserted-by":"crossref","unstructured":"J. Chorowski, N. Jaitly, Towards better decoding and language model integration in sequence to sequence models, arXiv preprint arXiv:1612.02695 (2016).","DOI":"10.21437\/Interspeech.2017-343"},{"key":"10.1016\/j.procs.2026.01.037_bib11","doi-asserted-by":"crossref","unstructured":"A. Zeyer, K. Irie, R. Schl\u00fcter, H. Ney, Improved training of end-to-end attention models for speech recognition, in: Interspeech 2018, interspeech2018, ISCA,2018.","DOI":"10.21437\/Interspeech.2018-1616"},{"key":"10.1016\/j.procs.2026.01.037_bib12","doi-asserted-by":"crossref","first-page":"434","DOI":"10.1109\/ASRU46091.2019.9003790","article-title":"A density ratio approach to language model fusion in end-to-end automatic speech recognition","author":"McDermott","year":"2019","journal-title":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"},{"key":"10.1016\/j.procs.2026.01.037_bib13","series-title":"Massively multilingual shallow fusion with large language models, in: ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"1","author":"Hu","year":"2023"},{"key":"10.1016\/j.procs.2026.01.037_bib14","doi-asserted-by":"crossref","unstructured":"I. Thorbecke, J. Zuluaga-Gomez, E. Villatoro-Tello, S. Kumar, P. Rangappa, S. Burdisso, P. Motlicek, K. Pandia, A. Ganapathiraju, Fast streaming transducer asr prototyping via knowledge distillation with whisper, arXiv preprint arXiv:2409.13499 (2024).","DOI":"10.18653\/v1\/2024.findings-emnlp.976"},{"key":"10.1016\/j.procs.2026.01.037_bib15","doi-asserted-by":"crossref","unstructured":"Z. Gong, D. Saito, N. Minematsu, Entropy-based dynamic rescoring with language model in e2e asr systems, Applied Sciences 12 (2022).","DOI":"10.3390\/app12199690"},{"key":"10.1016\/j.procs.2026.01.037_bib16","unstructured":"I. A. El-khair, 1.5 billion words arabic corpus, 2016. arXiv:1611.04033."},{"key":"10.1016\/j.procs.2026.01.037_bib17","series-title":"Fleurs: Few-shot learning evaluation of universal representations of speech, in: 2022 IEEE Spoken Language Technology Workshop (SLT)","first-page":"798","author":"Conneau","year":"2023"},{"key":"10.1016\/j.procs.2026.01.037_bib18","series-title":"Masc: Massive arabic speech corpus, in: 2022 IEEE Spoken Language Technology Workshop (SLT)","first-page":"1006","author":"Al-Fetyani","year":"2023"}],"container-title":["Procedia Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1877050926000372?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1877050926000372?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T11:33:06Z","timestamp":1777894386000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1877050926000372"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":18,"alternative-id":["S1877050926000372"],"URL":"https:\/\/doi.org\/10.1016\/j.procs.2026.01.037","relation":{},"ISSN":["1877-0509"],"issn-type":[{"value":"1877-0509","type":"print"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Confidence Gated Fusion: Dynamic Language Model Integration for Adapting Pretrained Multilingual ASR Models with Text-Only Data","name":"articletitle","label":"Article Title"},{"value":"Procedia Computer Science","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.procs.2026.01.037","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Author(s). Published by Elsevier B.V.","name":"copyright","label":"Copyright"}]}}