{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:57:36Z","timestamp":1776887856970,"version":"3.51.2"},"reference-count":24,"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\/icassp49660.2025.10890057","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":3,"title":["Contextual ASR with Retrieval Augmented Large Language Model"],"prefix":"10.1109","author":[{"given":"Cihan","family":"Xiao","sequence":"first","affiliation":[{"name":"Johns Hopkins University,Center for Language and Speech Processing,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zejiang","family":"Hou","sequence":"additional","affiliation":[{"name":"AWS AI Labs,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"Garcia-Romero","sequence":"additional","affiliation":[{"name":"AWS AI Labs,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kyu J","family":"Han","sequence":"additional","affiliation":[{"name":"AWS AI Labs,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-749"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447438"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1471"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-industry.60"},{"key":"ref5","first-page":"5132","article-title":"DOC-RAG: ASR language model personalization with domain-distributed co-occurrence retrieval augmentation","volume-title":"Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)","author":"Mathur"},{"key":"ref6","article-title":"Retrieval augmented generation on audio data with langchain and chroma","author":"O\u2019Connor","year":"2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389703"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832146"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447448"},{"key":"ref10","article-title":"Speechverse: A large-scale generalizable audio language model","author":"Das","year":"2024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10447605"},{"key":"ref12","article-title":"Multi-modal retrieval for large language model based speech recognition","volume-title":"ACL 2024","author":"Kolehmainen"},{"key":"ref13","article-title":"Mistral 7b","author":"Jiang","year":"2023"},{"key":"ref14","article-title":"Qwen-audio: Advancing universal audio understanding via unified large-scale audio-language models","author":"Chu","year":"2023"},{"key":"ref15","article-title":"Robust speech recognition via largescale weak supervision","author":"Radford","year":"2022"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1915"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1915"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.80"},{"key":"ref19","article-title":"Conec: Earnings call dataset with real-world contexts for benchmarking contextual speech recognition","volume-title":"LREC-COLING 2024","author":"Huang"},{"key":"ref20","first-page":"79","article-title":"Europarl: A parallel corpus for statistical machine translation","volume-title":"Proceedings of Machine Translation Summit X: Papers","author":"Koehn"},{"key":"ref21","article-title":"Mpnet: Masked and permuted pre-training for language understanding","author":"Song","year":"2020"},{"key":"ref22","article-title":"The faiss library","author":"Douze","year":"2024"},{"key":"ref23","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021"},{"key":"ref24","article-title":"The claude 3 model family: Opus, sonnet, haiku","year":"2024"}],"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\/10890057.pdf?arnumber=10890057","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:25:09Z","timestamp":1774416309000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890057\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890057","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}