{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:11:02Z","timestamp":1761894662102,"version":"build-2065373602"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11209855","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Teochew-Wild: The First In-the-wild Teochew Dataset with Orthographic Annotations"],"prefix":"10.1109","author":[{"given":"Linrong","family":"Pan","sequence":"first","affiliation":[{"name":"South China University of Technology,School of Computer Science and Engineering,Guangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenglong","family":"Jiang","sequence":"additional","affiliation":[{"name":"South China University of Technology,School of Computer Science and Engineering,Guangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gaoze","family":"Hou","sequence":"additional","affiliation":[{"name":"Guangzhou No.6 Middle School,Guangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying","family":"Gao","sequence":"additional","affiliation":[{"name":"South China University of Technology,School of Computer Science and Engineering,Guangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746682"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832365"},{"key":"ref3","first-page":"4218","article-title":"Common voice: A massively-multilingual speech corpus","volume-title":"Proceedings of the Twelfth Language Resources and Evaluation Conference","author":"Ardila"},{"key":"ref4","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International conference on machine learning","author":"Radford"},{"article-title":"Seed-asr: Understanding diverse speech and contexts with llm-based speech recognition","year":"2024","author":"Bai","key":"ref5"},{"article-title":"Moonshine: Speech recognition for live transcription and voice commands","year":"2024","author":"Jeffries","key":"ref6"},{"article-title":"Maskgct: Zero-shot text-to-speech with masked generative codec transformer","year":"2024","author":"Wang","key":"ref7"},{"article-title":"Neural codec language models are zero-shot text to speech synthesizers","year":"2023","author":"Wang","key":"ref8"},{"article-title":"Cosyvoice: A scalable multilingual zero-shot text-to-speech synthesizer based on supervised semantic tokens","year":"2024","author":"Du","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.313"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683536"},{"issue":"97","key":"ref12","first-page":"1","article-title":"Scaling speech technology to 1,000+ languages","volume":"25","author":"Pratap","year":"2024","journal-title":"Journal of Machine Learning Research"},{"key":"ref13","first-page":"6849","article-title":"Experiments on speech synthesis for teochew, can taiwanese help?","volume-title":"Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)","author":"Magistry"},{"key":"ref14","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"article-title":"Low-resource self-supervised learning with ssl-enhanced tts","year":"2023","author":"Hsu","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3184480"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403331"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447759"},{"key":"ref21","first-page":"271","volume-title":"Cstr vctk corpus: English multi-speaker corpus for cstr voice cloning toolkit (version 0.92)","author":"Yamagishi","year":"2019"},{"article-title":"AISHELL-3: A Multi-Speaker Mandarin TTS Corpus","volume-title":"Proc. of Interspeech","author":"Yao","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1965"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2343"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746108"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","volume-title":"International Conference on Learning Representations","author":"Ren","key":"ref28"},{"key":"ref29","first-page":"17022","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume":"33","author":"Kong","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.aacl-demo.6"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2025,6,30]]},"location":"Nantes, France","end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11209855.pdf?arnumber=11209855","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:32:50Z","timestamp":1761888770000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11209855\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11209855","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}