{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:25:22Z","timestamp":1774419922505,"version":"3.50.1"},"reference-count":40,"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\/icassp49660.2025.10890616","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Speech Recognition Rescoring with Large Speech-Text Foundation Models"],"prefix":"10.1109","author":[{"given":"Prashanth Gurunath","family":"Shivakumar","sequence":"first","affiliation":[{"name":"Amazon Science,Seattle,Washington,U.S.A"}]},{"given":"Jari","family":"Kolehmainen","sequence":"additional","affiliation":[{"name":"Amazon Science,Seattle,Washington,U.S.A"}]},{"given":"Aditya","family":"Gourav","sequence":"additional","affiliation":[{"name":"Amazon Science,Seattle,Washington,U.S.A"}]},{"given":"Yi","family":"Gu","sequence":"additional","affiliation":[{"name":"Amazon Science,Seattle,Washington,U.S.A"}]},{"given":"Ankur","family":"Gandhe","sequence":"additional","affiliation":[{"name":"Amazon Science,Seattle,Washington,U.S.A"}]},{"given":"Ariya","family":"Rastrow","sequence":"additional","affiliation":[{"name":"Amazon Science,Seattle,Washington,U.S.A"}]},{"given":"Ivan","family":"Bulyko","sequence":"additional","affiliation":[{"name":"Amazon Science,Seattle,Washington,U.S.A"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2022"},{"key":"ref2","article-title":"An empirical study of efficient ASR rescoring with transformers","author":"Huang","year":"2019"},{"key":"ref3","first-page":"1081","article-title":"Effective sentence scoring method using BERT for speech recognition","volume-title":"Asian Conference on Machine Learning","author":"Shin"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.240"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688175"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11123"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054335"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053606"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1341"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1981"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-990"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389787"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2128"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747118"},{"key":"ref15","first-page":"1336","article-title":"On generative spoken language modeling from raw audio","volume":"9","author":"Lakhotia","year":"2021","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.593"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00545"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.63"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.769"},{"key":"ref20","article-title":"AudioPaLM: A large language model that can speak and listen","author":"Rubenstein","year":"2023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10447112"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.438"},{"key":"ref23","article-title":"SpiRit-LM: Interleaved spoken and written language model","author":"Nguyen","year":"2024"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.1055"},{"key":"ref25","article-title":"LMs with a voice: Spoken language modeling beyond speech tokens","author":"Nachmani","year":"2023"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445874"},{"key":"ref27","article-title":"Salmonn: Towards generic hearing abilities for large language models","author":"Tang","year":"2023"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2826"},{"key":"ref31","article-title":"The people\u2019s speech: A large-scale diverse english speech recognition dataset for commercial usage","author":"Galvez","year":"2021"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-2027"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-99579-3_21"},{"key":"ref34","article-title":"OPT: Open pre-trained transformer language models","author":"Zhang","year":"2022"},{"key":"ref35","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref36","article-title":"Textually pretrained speech language models","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Hassid"},{"key":"ref37","article-title":"RedPajama: an open dataset for training large language models","year":"2023"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.3115\/1075527.1075614"},{"key":"ref39","first-page":"4218","article-title":"Common Voice: A massively-multilingual speech corpus","volume-title":"Proceedings of the Twelfth Language Resources and Evaluation Conference","author":"Ardila"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/11677482_3"}],"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\/10890616.pdf?arnumber=10890616","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:25:27Z","timestamp":1774416327000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890616\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890616","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}