{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T12:34:26Z","timestamp":1783427666773,"version":"3.54.6"},"reference-count":26,"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\/icassp49660.2025.10887651","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":7,"title":["Large Language Model Should Understand Pinyin for Chinese ASR Error Correction"],"prefix":"10.1109","author":[{"given":"Yuang","family":"Li","sequence":"first","affiliation":[{"name":"Huawei Translation Services Center,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaosong","family":"Qiao","sequence":"additional","affiliation":[{"name":"Huawei Translation Services Center,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaofeng","family":"Zhao","sequence":"additional","affiliation":[{"name":"Huawei Translation Services Center,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huan","family":"Zhao","sequence":"additional","affiliation":[{"name":"Huawei Translation Services Center,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Tang","sequence":"additional","affiliation":[{"name":"Huawei Translation Services Center,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Min","family":"Zhang","sequence":"additional","affiliation":[{"name":"Huawei Translation Services Center,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Yang","sequence":"additional","affiliation":[{"name":"Huawei Translation Services Center,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"577","article-title":"Attention-based models for speech recognition","volume-title":"Proc. NeurIPS","author":"Chorowski"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref3","article-title":"Sequence transduction with recurrent neural networks","volume-title":"Proc. ICML","author":"Graves"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.367"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446621"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.432"},{"key":"ref7","article-title":"Can generative large language models perform asr error correction?","author":"Ma","year":"2023"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389673"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29863"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-44699-3_7"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-103"},{"key":"ref12","article-title":"Qwen-audio: Advancing universal audio understanding via unified large-scale audio-language models","author":"Chu","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.618"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688053"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-987"},{"key":"ref16","article-title":"GPT-4 technical report","year":"2023"},{"key":"ref17","article-title":"Glm-130b: An open bilingual pre-trained model","volume-title":"Proc. ICLR","author":"Zeng"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/icsda.2017.8384449"},{"key":"ref19","article-title":"Common voice: A massively-multilingual speech corpus","volume-title":"Proc. LREC","author":"Ardila"},{"key":"ref20","article-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2022"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.1997.659110"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.459"},{"key":"ref23","first-page":"169","article-title":"Minimum bayes-risk decoding for statistical machine translation","volume-title":"Proc. HLT-NAACL","author":"Kumar"},{"key":"ref24","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. ICLR","author":"Hu"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-demos.38"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746955"}],"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\/10887651.pdf?arnumber=10887651","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:21:58Z","timestamp":1774416118000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10887651\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10887651","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}