{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T16:11:16Z","timestamp":1781021476878,"version":"3.54.1"},"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"}],"funder":[{"DOI":"10.13039\/501100003452","name":"Innovation and Technology Commission","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003452","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10887601","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":2,"title":["Integrating Potential Pronunciations for Enhanced Mispronunciation Detection and Diagnosis Ability in LLMs"],"prefix":"10.1109","author":[{"given":"Minglin","family":"Wu","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong,Department of Systems Engineering and Engineering Management,Hong Kong SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Xu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Department of Systems Engineering and Engineering Management,Hong Kong SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xueyuan","family":"Chen","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Department of Systems Engineering and Engineering Management,Hong Kong SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Helen","family":"Meng","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Department of Systems Engineering and Engineering Management,Hong Kong SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(99)00044-8"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1121\/1.5011159"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2363"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-777"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-870"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2012-238"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2387413"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682654"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052975"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1467"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1344"},{"key":"ref12","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems","author":"Baevski"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448480"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447007"},{"key":"ref16","article-title":"Gpt-4 technical report","year":"2024"},{"key":"ref17","article-title":"Gemini: A family of highly capable multimodal models","author":"Team","year":"2023"},{"key":"ref18","author":"Yang","year":"2024","journal-title":"Qwen2 technical report"},{"key":"ref19","article-title":"Palm: Scaling language modeling with pathways","author":"Chowdhery","year":"2022"},{"key":"ref20","article-title":"Palm-e: An embodied multimodal language model","author":"Driess","year":"2023"},{"key":"ref21","article-title":"Pandagpt: One model to instruction-follow them all","author":"Su","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref23","article-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality","author":"Chiang","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i21.30570"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10447605"},{"key":"ref26","article-title":"An embarrassingly simple approach for llm with strong asr capacity","author":"Ma","year":"2024"},{"key":"ref27","author":"Chu","year":"2024","journal-title":"Qwen2-audio technical report"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.1055"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref30","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1772"},{"key":"ref32","article-title":"Development of automatic speech recognition and synthesis technologies to support chinese learners of english : The cuhk experience development of automatic speech recognition and synthesis technologies to support chinese learners of english : The cuhk experience","author":"Meng","year":"2010"},{"key":"ref33","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"International Conference on Learning Representations","author":"Hu"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2010.5684845"}],"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\/10887601.pdf?arnumber=10887601","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:23:34Z","timestamp":1774416214000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10887601\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10887601","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}