{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:44:39Z","timestamp":1776883479104,"version":"3.51.2"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10448105","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"10061-10065","source":"Crossref","is-referenced-by-count":5,"title":["G2PU: Grapheme-To-Phoneme Transducer with Speech Units"],"prefix":"10.1109","author":[{"given":"Heting","family":"Gao","sequence":"first","affiliation":[{"name":"University of Illinois at Urbana-Champaign (UIUC),USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mark","family":"Hasegawa-Johnson","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign (UIUC),USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chang D.","family":"Yoo","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science and Technology (KAIST),Korean"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Unsupervised speech recognition","volume":"34","author":"Baevski","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-816"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639655"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2513"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1843"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1009"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-216"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1386"},{"key":"ref9","first-page":"77","article-title":"Improved pronunciation modeling by properly integrating better approaches for baseform generation, ranking and pruning","volume-title":"ISCA Workshop on Pronunciation Modeling and Lexical Access (PMLA)","author":"Tsai"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-59430-5_1"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1235"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1094"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-546"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-538"},{"key":"ref15","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019","journal-title":"ArXiv"},{"key":"ref16","first-page":"30","article-title":"Disambiguation of Chinese polyphonic characters","volume-title":"The First International Workshop on MultiMedia Annotation (MMA2001)","volume":"1","author":"Zhang"},{"key":"ref17","article-title":"KAKASI - kanji kana simple inverter","year":"1999"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1907.11692"},{"key":"ref19","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"Baevski","year":"2020","journal-title":"NeurIPS"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref21","first-page":"18003","article-title":"Contentvec: An improved self-supervised speech representation by disentangling speakers","volume-title":"International Conference on Machine Learning","author":"Qian"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-502"},{"key":"ref23","first-page":"1336","article-title":"On generative spoken language modeling from raw audio","volume":"9","author":"Lakhotia","year":"2021","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-475"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-755"},{"key":"ref28","article-title":"Corpus of spontaneous Japanese: Its design and evaluation","volume-title":"ISCA & IEEE Workshop on Spontaneous Speech Processing and Recognition","author":"Maekawa"},{"key":"ref29","article-title":"United Nations Proceedings Speech","author":"Chay","year":"2023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413425"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10448105.pdf?arnumber=10448105","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:52:27Z","timestamp":1722574347000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10448105\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10448105","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}