{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T06:55:37Z","timestamp":1769842537478,"version":"3.49.0"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"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":[[2023,12,16]]},"DOI":"10.1109\/asru57964.2023.10389730","type":"proceedings-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T18:38:40Z","timestamp":1705689520000},"page":"1-8","source":"Crossref","is-referenced-by-count":7,"title":["Leveraging the Multilingual Indonesian Ethnic Languages Dataset In Self-Supervised Models for Low-Resource ASR Task"],"prefix":"10.1109","author":[{"given":"Sakriani","family":"Sakti","sequence":"first","affiliation":[{"name":"Japan Advanced Institute of Science and Technology,Japan"}]},{"given":"Benita Angela","family":"Titalim","sequence":"additional","affiliation":[{"name":"Japan Advanced Institute of Science and Technology,Japan"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.500"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2904"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2743"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1755"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.580"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1316"},{"key":"ref8","article-title":"Google USM: Scaling automatic speech recognition beyond 100 languages","author":"Zhang","year":"2023","journal-title":"arXiv preprint arXiv:2303.01037"},{"key":"ref9","article-title":"Scaling speech technology to 1,000+ languages","author":"Pratap","year":"2023","journal-title":"arXiv preprint arXiv:2305.13516"},{"key":"ref10","volume-title":"Indonesian as a unifying language of wider communication: A historical and sociolinguistic perspective, Pacific Linguistics","author":"Abas","year":"1987"},{"key":"ref11","volume-title":"Language policy in Indonesia: The promotion of a national language amidst ethnic diversity","author":"Bertand","year":"2003"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1080\/14631360600734400"},{"key":"ref13","volume-title":"Language Treasures in Indonesia","author":"Lauder","year":"2005"},{"key":"ref14","article-title":"Dynamics of the sentences system in Balinese-Malay language","volume":"12","author":"Suparwa","year":"2017","journal-title":"Melayu"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2012.6422469"},{"key":"ref16","first-page":"19","article-title":"Development of Indonesian large vocabulary continuous speech recognition system within A-STAR project","volume-title":"in Proc. IJCNLP Workshop on TCAST","author":"Sakti"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2013.6709907"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2004-366"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2011.07.001"},{"key":"ref20","first-page":"46","article-title":"Recent progress in developing grapheme-based speech recognition for Indonesian ethnic languages: Javanese, Sundanese, Balinese and Bataks","volume-title":"in Proc. the Workshop on Spoken Language Technologies for Underresourced Languages (SLTU)","author":"Sakti"},{"key":"ref21","first-page":"3145","article-title":"An efficient algorithm to search for a minimum sentence set for collecting speech database","volume-title":"in Proc. the International Congress of Phonetic Sciences (ICPhS)","author":"Zhang"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.868"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2013.07.001"},{"key":"ref24","article-title":"Common Voice: A massively-multilingual speech corpus","author":"Ardila","year":"2020","journal-title":"arXiv preprint"},{"key":"ref25","article-title":"FLEURS: Few-shot learning evaluation of universal representations of speech","author":"Conneau","year":"2022","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/SLTU.2018-14"},{"key":"ref27","first-page":"6494","article-title":"Open-source multi-speaker speech corpora for building gujarati, kannada, malay-alam, marathi, tamil and telugu speech synthesis systems","volume-title":"in Proc. the Language Resources and Evaluation Conference (LREC)","author":"He"},{"key":"ref28","first-page":"21","article-title":"Open-source high quality speech datasets for basque, catalan and galician","volume-title":"in Proc. Proc. the Joint Spoken Language Technologies for Under-Resourced Languages (SLTU) and Collaboration and Computing for Under-Resourced Languages (CCURL) Workshop (SLTU-CCURL)","author":"Kjartansson"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2448"},{"key":"ref30","article-title":"The M-AILABS speech dataset","author":"Solak","year":"2018"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10796"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.96"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.americasnlp-1.7"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2826"},{"key":"ref35","article-title":"The nchlt speech corpus of the south african languages","volume-title":"in Proc. the Workshop on Spoken Language Technologies for Under-resourced Languages (SLTU)","author":"Barnard"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-31389-9_9"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-017-9410-y"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.80"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref41","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"Baevski","year":"2020","journal-title":"arXiv preprint"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-143"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref44","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2017","journal-title":"arXiv preprint"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2680"}],"event":{"name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Taipei, Taiwan","start":{"date-parts":[[2023,12,16]]},"end":{"date-parts":[[2023,12,20]]}},"container-title":["2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10388490\/10389614\/10389730.pdf?arnumber=10389730","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T16:36:23Z","timestamp":1706027783000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10389730\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,16]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/asru57964.2023.10389730","relation":{},"subject":[],"published":{"date-parts":[[2023,12,16]]}}}