{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T06:41:38Z","timestamp":1776235298992,"version":"3.50.1"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3681804","type":"journal-article","created":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T20:07:12Z","timestamp":1775678832000},"page":"1-1","source":"Crossref","is-referenced-by-count":0,"title":["Toward Unified Chinese Multi-Dialectal Speech Recognition via Pinyin Intermediate Representation"],"prefix":"10.1109","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-5462-5497","authenticated-orcid":false,"given":"Junjie","family":"Cheng","sequence":"first","affiliation":[{"name":"Nanjing Tech University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaorong","family":"Wu","sequence":"additional","affiliation":[{"name":"Nanhang Jincheng College, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Scaling speech technology to 1,000+ languages","author":"Pratap","year":"2023","journal-title":"arXiv:2305.13516"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/access.2024.3364098"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/access.2025.3539613"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/access.2022.3204677"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.lingua.2008.10.001"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3390\/languages10060127"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1162\/coli_a_00366"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1515\/flin-2024-2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/access.2024.3488186"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2024.3363414"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3390\/app14209533"},{"issue":"3","key":"ref12","first-page":"786","article-title":"Amdo-Chinese speech translation dataset","volume":"7","author":"Zengzhuoma","year":"2024","journal-title":"Data Intell."},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2022.945973"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1075\/aplv.20004.li"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1017\/s095439452300008x"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-023-10668-0"},{"key":"ref17","article-title":"KeSpeech: An open source speech dataset of Mandarin and its eight subdialects","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst. Datasets Benchmarks Track Round 2","author":"Tang"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3473499"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/access.2025.3583708"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/access.2025.3634679"},{"issue":"2","key":"ref21","first-page":"103","article-title":"A quantitative model of phonetic differences among Chinese dialects","author":"Chen","year":"2019","journal-title":"J. Beijing Norm. Univ. Soc. Sci."},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3421558.3421577"},{"key":"ref23","volume-title":"Linguistics: A Concise Course Book","author":"Hu","year":"2013"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3390\/e24101429"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.32604\/cmc.2019.05636"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.32604\/cmc.2022.027092"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-374"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3389021"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/access.2023.3259901"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2024.3378110"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3390\/s22103683"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-10015"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/asru51503.2021.9688053"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/iscslp63861.2024.10800477"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/icsda.2017.8384449"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2015.10.006"},{"key":"ref37","article-title":"Mengzi: Towards lightweight yet ingenious pre-trained models for Chinese","author":"Zhang","year":"2021","journal-title":"arXiv:2110.06696"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-96-1045-7_15"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19-4009"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.wocn.2016.08.004"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.wocn.2019.100918"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1121\/10.0026374"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/6514899\/11477766.pdf?arnumber=11477766","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T05:41:23Z","timestamp":1776231683000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11477766\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3681804","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}