{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T17:58:03Z","timestamp":1768499883354,"version":"3.49.0"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,17]],"date-time":"2024-10-17T00:00:00Z","timestamp":1729123200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,17]],"date-time":"2024-10-17T00:00:00Z","timestamp":1729123200000},"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":[[2024,10,17]]},"DOI":"10.1109\/o-cocosda64382.2024.10800336","type":"proceedings-article","created":{"date-parts":[[2024,12,20]],"date-time":"2024-12-20T18:56:08Z","timestamp":1734720968000},"page":"1-6","source":"Crossref","is-referenced-by-count":3,"title":["Enhancing Indonesian Automatic Speech Recognition: Evaluating Multilingual Models with Diverse Speech Variabilities"],"prefix":"10.1109","author":[{"given":"Aulia","family":"Adila","sequence":"first","affiliation":[{"name":"Institut Teknologi Bandung,Indonesia"}]},{"given":"Dessi","family":"Lestari","sequence":"additional","affiliation":[{"name":"Institut Teknologi Bandung,Indonesia"}]},{"given":"Ayu","family":"Purwarianti","sequence":"additional","affiliation":[{"name":"Institut Teknologi Bandung,Indonesia"}]},{"given":"Dipta","family":"Tanaya","sequence":"additional","affiliation":[{"name":"University of Indonesia,Indonesia"}]},{"given":"Kurniawati","family":"Azizah","sequence":"additional","affiliation":[{"name":"University of Indonesia,Indonesia"}]},{"given":"Sakriani","family":"Sakti","sequence":"additional","affiliation":[{"name":"Japan Advanced Institute of Science and Technology,Japan"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-5779-3"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-2620"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18280\/isi.270614"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.33480\/pilar.v20i1.4633"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389730"},{"key":"ref6","article-title":"Scaling Speech Technology to 1,000+ Languages","volume-title":"arXiv:2305.13516","author":"Pratap","year":"2023"},{"key":"ref7","author":"Radford","year":"2022","journal-title":"Ro-bust Speech Recognition via Large-Scale Weak Super-vision"},{"key":"ref8","author":"Sakti","year":"2005","journal-title":"Rapid Development of Initial Indonesian Phoneme-based Speech Recognition Using The Cross-Language Approach"},{"key":"ref9","article-title":"Development of Indonesian large vocabulary continu-ous speech recognition system within a-STAR project","volume-title":"Proceedings of the Workshop on Technologies and Corpora for Asia-Pacific Speech Translation (TCAST)","author":"Sakti","year":"2008"},{"key":"ref10","author":"Baevski","year":"2020","journal-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2013.6709907"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2004-366"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2011.07.001"},{"key":"ref14","article-title":"Recent progress in developing grapheme-based speech recognition for indonesian ethnic languages: Javanese, sundanese, ba-1inese and bataks","volume-title":"Workshop on Spoken Language Technologies for Under-resourced Languages","author":"Sakti","year":"2014"},{"key":"ref15","article-title":"Common voice: A massively-multilingual speech cor-pus","author":"Ardila","year":"2019","journal-title":"CoRR"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/slt54892.2023.10023141"},{"key":"ref17","volume-title":"Indonesian speech datasets"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/MELCON.2010.5476314"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref20","volume-title":"Hugging face - the ai community building the future","author":"Face","year":"2024"},{"key":"ref21","author":"Kingma","year":"2017","journal-title":"Adam: A method for stochastic optimization"},{"key":"ref22","first-page":"187","article-title":"KenLM: Faster and smaller language model queries","volume-title":"Proceedings of the Sixth Work-shop on Statistical Machine Translation","author":"Heafield"}],"event":{"name":"2024 27th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","location":"Hsinchu City, Taiwan","start":{"date-parts":[[2024,10,17]]},"end":{"date-parts":[[2024,10,19]]}},"container-title":["2024 27th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10799946\/10799972\/10800336.pdf?arnumber=10800336","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,21]],"date-time":"2024-12-21T06:19:02Z","timestamp":1734761942000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10800336\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,17]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/o-cocosda64382.2024.10800336","relation":{},"subject":[],"published":{"date-parts":[[2024,10,17]]}}}