{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:57:37Z","timestamp":1776887857828,"version":"3.51.2"},"reference-count":19,"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\/icassp49660.2025.10888744","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":5,"title":["Contextualization of ASR with LLM using phonetic retrieval-based augmentation"],"prefix":"10.1109","author":[{"given":"Zhihong","family":"Lei","sequence":"first","affiliation":[{"name":"Apple"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xingyu","family":"Na","sequence":"additional","affiliation":[{"name":"Apple"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingbin","family":"Xu","sequence":"additional","affiliation":[{"name":"Apple"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ernest","family":"Pusateri","sequence":"additional","affiliation":[{"name":"Apple"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christophe","family":"Van Gysel","sequence":"additional","affiliation":[{"name":"Apple"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuanyuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Apple"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiyi","family":"Han","sequence":"additional","affiliation":[{"name":"Apple"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhen","family":"Huang","sequence":"additional","affiliation":[{"name":"Apple"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"AudioPaLM: A large language model that can speak and listen","author":"Rubenstein","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447605"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.787"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445874"},{"key":"ref5","article-title":"ChatGPT-4 Turbo with vision","year":"2023"},{"key":"ref6","first-page":"31665","article-title":"HyPoradise: An open baseline for generative speech recognition with large language models","volume":"36","author":"Chen","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447571"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639034"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2136"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446898"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447553"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.459"},{"key":"ref13","first-page":"9459","article-title":"Retrievalaugmented generation for knowledge-intensive nlp tasks","volume":"33","author":"Lewis","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389720"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-industry.12"},{"key":"ref18","article-title":"Mistral 7B","author":"Jiang","year":"2023"},{"key":"ref19","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"International Conference on Learning Representations","author":"Hu"}],"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\/10888744.pdf?arnumber=10888744","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:22:20Z","timestamp":1774416140000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888744\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888744","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}