{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:18:00Z","timestamp":1763191080907,"version":"3.45.0"},"reference-count":36,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"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\/ijcnn64981.2025.11228737","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Unsupervised Speech Unit Boundary Detection Guided by Linguistic Rule Knowledge"],"prefix":"10.1109","author":[{"given":"Sanlong","family":"Jiang","sequence":"first","affiliation":[{"name":"Kunming University of Science and Technology,Faculty of Information Engineering and Automation,Kunming,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ling","family":"Dong","sequence":"additional","affiliation":[{"name":"Kunming University of Science and Technology,Faculty of Information Engineering and Automation,Kunming,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenjun","family":"Wang","sequence":"additional","affiliation":[{"name":"Kunming University of Science and Technology,Faculty of Information Engineering and Automation,Kunming,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengtao","family":"Yu","sequence":"additional","affiliation":[{"name":"Kunming University of Science and Technology,Faculty of Information Engineering and Automation,Kunming,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shengxiang","family":"Gao","sequence":"additional","affiliation":[{"name":"Kunming University of Science and Technology,Faculty of Information Engineering and Automation,Kunming,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref2","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International conference on machine learning","author":"Radford"},{"issue":"97","key":"ref3","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":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1800"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2068"},{"key":"ref6","first-page":"27826","article-title":"Unsupervised speech recognition","volume":"34","author":"Baevski","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023187"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096977"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4110"},{"article-title":"Unsupervised neural machine translation","volume-title":"6th International Conference on Learning Representations, ICLR 2018","author":"Artetxe","key":"ref10"},{"article-title":"Word translation without parallel data","volume-title":"International conference on learning representations","author":"Lample","key":"ref11"},{"article-title":"Unsupervised machine translation using monolingual corpora only","volume-title":"International Conference on Learning Representations","author":"Lample","key":"ref12"},{"key":"ref13","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2022.02.005"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2398"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1544"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3180684"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746102"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-50"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3229264"},{"key":"ref21","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":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"issue":"2","key":"ref25","first-page":"269","article-title":"Finite-state transducers in language and speech processing","volume":"23","author":"Mohri","year":"1997","journal-title":"Computational linguistics"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1006\/csla.2001.0184"},{"journal-title":"spacy: Industrial-strength natural language processing in python","year":"2020","author":"Honnibal","key":"ref27"},{"article-title":"Timit acoustic-phonetic continuous speech corpus","year":"1993","author":"Garofolo","key":"ref28"},{"article-title":"Unsupervised speech recognition via segmental empirical output distribution matching","volume-title":"International Conference on Learning Representations","author":"Yeh","key":"ref29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.06.005"},{"volume-title":"Kyubyong & Kim. g2pe","year":"2019","author":"Park","key":"ref32"},{"article-title":"The kaldi speech recognition toolkit","volume-title":"IEEE 2011 workshop on automatic speech recognition and understanding","author":"Povey","key":"ref33"},{"key":"ref34","first-page":"187","article-title":"Kenlm: Faster and smaller language model queries","volume-title":"Proceedings of the sixth workshop on statistical machine translation","author":"Heafield"},{"volume-title":"Natural language processing with Python: analyzing text with the natural language toolkit.","year":"2009","author":"Bird","key":"ref35"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462463"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2025,6,30]]},"location":"Rome, Italy","end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11228737.pdf?arnumber=11228737","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:13:56Z","timestamp":1763190836000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11228737\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11228737","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}