{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T14:06:18Z","timestamp":1730297178104,"version":"3.28.0"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"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":[[2023,1,9]]},"DOI":"10.1109\/slt54892.2023.10022827","type":"proceedings-article","created":{"date-parts":[[2023,1,27]],"date-time":"2023-01-27T18:54:03Z","timestamp":1674845643000},"page":"1067-1073","source":"Crossref","is-referenced-by-count":2,"title":["Phoneme Segmentation Using Self-Supervised Speech Models"],"prefix":"10.1109","author":[{"given":"Luke","family":"Strgar","sequence":"first","affiliation":[{"name":"University of Texas at Austin,Department of Computer Science"}]},{"given":"David","family":"Harwath","sequence":"additional","affiliation":[{"name":"University of Texas at Austin,Department of Computer Science"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053053"},{"key":"ref2","first-page":"1","article-title":"Phoneme boundary detection using deep bidirectional lstms","volume-title":"Speech Communication; 12. ITG Symposium","author":"Franke"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1386"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746880"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2398"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1874"},{"key":"ref7","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":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref9","article-title":"Applying wav2vec2. 0 to speech recognition in various low-resource languages","author":"Yi","year":"2020","journal-title":"arXiv preprint"},{"key":"ref10","article-title":"Arabic speech emotion recognition employing wav2vec2. 0 and hubert based on baved dataset","author":"Mohamed","year":"2021","journal-title":"arXiv preprint"},{"key":"ref11","article-title":"A fine-tuned wav2vec 2.0\/hubert benchmark for speech emotion recognition, speaker verification and spoken language understanding","author":"Wang","year":"2021","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747814"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.35111\/17gk-bn40"},{"key":"ref14","first-page":"265","article-title":"Buckeye corpus of conversational speech (2nd release)","author":"Pitt","year":"2007","journal-title":"Columbus, OH: Department of Psychology, Ohio State University"},{"journal-title":"Representation learning with contrastive predictive coding","year":"2018","author":"van den Oord","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/S0885-2308(03)00006-8"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2006-230"},{"key":"ref18","article-title":"A nonparametric Bayesian approach to acoustic model discovery","volume-title":"Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Lee","year":"2012"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2009-538"},{"key":"ref20","article-title":"Speech segmentation and clustering methods for a new speech recognition architecture","author":"R\u00e4s\u00e4nen","year":"2007","journal-title":"helsinki university of technology"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"}],"event":{"name":"2022 IEEE Spoken Language Technology Workshop (SLT)","start":{"date-parts":[[2023,1,9]]},"location":"Doha, Qatar","end":{"date-parts":[[2023,1,12]]}},"container-title":["2022 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10022052\/10022330\/10022827.pdf?arnumber=10022827","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T08:07:39Z","timestamp":1707811659000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10022827\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,9]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/slt54892.2023.10022827","relation":{},"subject":[],"published":{"date-parts":[[2023,1,9]]}}}