{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,28]],"date-time":"2025-06-28T06:24:43Z","timestamp":1751091883838,"version":"3.32.0"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62306260"],"award-info":[{"award-number":["62306260"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,11,7]]},"DOI":"10.1109\/iscslp63861.2024.10800392","type":"proceedings-article","created":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T19:11:17Z","timestamp":1734981077000},"page":"631-635","source":"Crossref","is-referenced-by-count":1,"title":["Improving Grapheme-to-Phoneme Conversion through In-Context Knowledge Retrieval with Large Language Models"],"prefix":"10.1109","author":[{"given":"Dongrui","family":"Han","sequence":"first","affiliation":[{"name":"Centre for Perceptual and Interactive Intelligence (CPII) Limited,Hong Kong"}]},{"given":"Mingyu","family":"Cui","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong"}]},{"given":"Jiawen","family":"Kang","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong"}]},{"given":"Xixin","family":"Wu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong"}]},{"given":"Xunying","family":"Liu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong"}]},{"given":"Helen","family":"Meng","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Fastspeech: Fast, robust and controllable text to speech","volume":"32","author":"Ren","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref3","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"Ren","year":"2020","journal-title":"arXiv preprint"},{"key":"ref4","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"International Conference on Machine Learning","author":"Kim","year":"2021"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2005.03.002"},{"key":"ref6","article-title":"Hidden markov models for grapheme to phoneme con-version","volume-title":"Ninth European Conference on Speech Communication and Technology","author":"Taylor","year":"2005"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2008.01.002"},{"key":"ref8","article-title":"Applying many-to-many alignments and hidden markov models to letter-to-phoneme conversion","volume-title":"Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics; Proceedings of the Main Conference","author":"Jiampojamarn","year":"2007"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953114"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178767"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-134"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3390\/app9061143"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-1954"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-538"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11066"},{"volume-title":"BERT: Pretraining of deep bidirectional transformers for language understanding","year":"2019","author":"Devlin","key":"ref16"},{"key":"ref17","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref18","first-page":"4129","article-title":"A structural probe for finding syn-tax in word representations","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Com-putational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)","author":"Hewitt","year":"2019"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.ijcnlp-main.45"},{"key":"ref20","article-title":"Enhancing conversational quality in language learning chatbots: An evaluation of gpt4 for asr error correction","author":"Mai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref21","article-title":"Can gener-ative large language models perform asr error correction?","author":"Ma","year":"2023","journal-title":"arXiv preprint"},{"key":"ref22","article-title":"Metaicl: Learning to learn in context","author":"Min","year":"2021","journal-title":"arXiv preprint"},{"key":"ref23","article-title":"Finetuned language models are zero-shot learners","author":"Wei","year":"2021","journal-title":"arXiv preprint"},{"key":"ref24","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref25","article-title":"Qlora: Efficient finetuning of quantized llms","volume":"36","author":"Dettmers","year":"2024","journal-title":"Advances in Neu-ral Information Processing Systems"}],"event":{"name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","start":{"date-parts":[[2024,11,7]]},"location":"Beijing, China","end":{"date-parts":[[2024,11,10]]}},"container-title":["2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10799944\/10799969\/10800392.pdf?arnumber=10800392","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,24]],"date-time":"2024-12-24T06:31:54Z","timestamp":1735021914000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10800392\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,7]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/iscslp63861.2024.10800392","relation":{},"subject":[],"published":{"date-parts":[[2024,11,7]]}}}