{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:24:12Z","timestamp":1775229852638,"version":"3.50.1"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890391","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":4,"title":["Delayed Fusion: Integrating Large Language Models into First-Pass Decoding in End-to-end Speech Recognition"],"prefix":"10.1109","author":[{"given":"Takaaki","family":"Hori","sequence":"first","affiliation":[{"name":"Apple"}]},{"given":"Martin","family":"Kocour","sequence":"additional","affiliation":[{"name":"Brno University of Technology"}]},{"given":"Adnan","family":"Haider","sequence":"additional","affiliation":[{"name":"Apple"}]},{"given":"Erik","family":"McDermott","sequence":"additional","affiliation":[{"name":"Apple"}]},{"given":"Xiaodan","family":"Zhuang","sequence":"additional","affiliation":[{"name":"Brno University of Technology"}]}],"member":"263","reference":[{"key":"ref1","article-title":"GPT-4 technical report","author":"Achiam","year":"2023"},{"key":"ref2","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"issue":"240","key":"ref3","first-page":"1","article-title":"PaLM: Scaling language modeling with pathways","volume":"24","author":"Chowdhery","year":"2023","journal-title":"Journal of Machine Learning Research"},{"key":"ref4","article-title":"Mistral 7b","author":"Jiang","year":"2023"},{"key":"ref5","article-title":"Large language models: A survey","author":"Minaee","year":"2024"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref7","article-title":"AudioPaLM: A large language model that can speak and listen","author":"Rubenstein","year":"2023"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389705"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2499"},{"key":"ref10","article-title":"LLaMA 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref11","article-title":"OpenLLaMA: An open reproduction of LLaMA","author":"Geng","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3328283"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1296"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639038"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746948"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1392"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6321"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/slt48900.2021.9383515"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.889790"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-532"},{"key":"ref21","article-title":"First-pass large vocabulary continuous speech recognition using bi-directional recurrent DNNs","author":"Hannun","year":"2014"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639693"},{"key":"ref23","article-title":"An empirical study of efficient ASR rescoring with transformers","author":"Huang","year":"2019"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747118"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10448361"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11123"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389673"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1616"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447120"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1983"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1048"},{"key":"ref35","article-title":"Sequence transduction with recurrent neural networks","volume-title":"Proc. ICML","author":"Graves"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10890391.pdf?arnumber=10890391","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:25:42Z","timestamp":1774416342000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890391\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890391","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}