{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T04:22:23Z","timestamp":1765254143051,"version":"3.37.3"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001691","name":"JSPS KAKENHI Grant-in-Aid for Scientific Research","doi-asserted-by":"publisher","award":["19H1225100"],"award-info":[{"award-number":["19H1225100"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3077441","type":"journal-article","created":{"date-parts":[[2021,5,4]],"date-time":"2021-05-04T20:58:43Z","timestamp":1620161923000},"page":"70758-70774","source":"Crossref","is-referenced-by-count":3,"title":["Improved Transcription and Speaker Identification System for Concurrent Speech in Bahasa Indonesia Using Recurrent Neural Network"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7909-5887","authenticated-orcid":false,"given":"Muhammad Bagus","family":"Andra","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tsuyoshi","family":"Usagawa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"DARPA TIMIT acoustic phonetic continuous speech corpus CDROM","year":"1993","author":"garofolo","key":"ref39"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2892"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952154"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"ref31","first-page":"201","article-title":"Review of multi-channel source separation in realistic environments","author":"jafari","year":"2010","journal-title":"Proc 13th Australas Int Conf Speech Sci Technol"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2006.12.006"},{"key":"ref37","article-title":"A unified speaker adaptation method for speech synthesis using transcribed and untranscribed speech with backpropagation","author":"luong","year":"2019","journal-title":"arXiv 1906 07414"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683138"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952118"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461477"},{"key":"ref28","first-page":"67","article-title":"Single channel speech enhancement for deep convolutional neural network feature using EM-Kalman filter","author":"andra","year":"2017","journal-title":"Proc Acoust Soc Japan Student Meeting Kyuushu"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICINIS.2015.35"},{"key":"ref29","article-title":"Speech enhancement: Application of the Kalman filter in the estimate-maximize (EM) framework","author":"sharon","year":"2005","journal-title":"Speech Enhancement"},{"journal-title":"Bahasa Indonesia between Faqs and Facts","year":"2005","author":"johannes","key":"ref2"},{"journal-title":"Penduduk Indonesia Hasil Sensus Penduduk 2010 (Result of Indonesia Population Census 2010)","first-page":"421","year":"2013","key":"ref1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2019.1911693"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2016.7918980"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2889606"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"1586","DOI":"10.1109\/PROC.1979.11540","article-title":"enhancement and bandwidth compression of noisy speech","volume":"67","author":"lim","year":"1979","journal-title":"Proceedings of the IEEE"},{"key":"ref23","first-page":"83","volume":"57","author":"bond","year":"2014","journal-title":"NUSA Linguistic studies of languages in and around Indonesia"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IWSDA.2007.4408401"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CCECE.2005.1556923"},{"journal-title":"CNN Indonesia","year":"2020","key":"ref50"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICEEI.2011.6021583"},{"journal-title":"Lwazi II Afrikaans Trajectory Tracking Corpus","year":"2021","author":"badenhorst","key":"ref57"},{"key":"ref56","first-page":"1","article-title":"The NCHLT speech corpus of the South African languages","author":"barnard","year":"2014","journal-title":"Proc SLTU"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2009.5278382"},{"key":"ref54","article-title":"Common voice: A massively-multilingual speech corpus","author":"rosana","year":"2019","journal-title":"arXiv 1912 06670"},{"key":"ref53","first-page":"173","article-title":"Deep speech 2: End-to-end speech recognition in English and Mandarin","author":"amodei","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ISESD.2016.7886734"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICSIGSYS.2019.8811080"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IC3INA.2018.8629525"},{"key":"ref40","doi-asserted-by":"crossref","first-page":"1037","DOI":"10.21437\/Interspeech.2004-366","article-title":"Indonesian speech recognition for hearing and speaking impaired people","author":"sakti","year":"2004","journal-title":"Proc INTERSPEECH"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ISITIA.2019.8937275"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IAC.2018.8780566"},{"journal-title":"NII-SRC Speech Resource Consortium TITML-IDN—Speech Resources Consortium","year":"2021","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2017.8282191"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1992.225858"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3023783"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2954342"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.4108\/eai.13-8-2019.2290196"},{"key":"ref3","first-page":"1","article-title":"Development of Indonesian large vocabulary continuous speech recognition system within A-STAR project","author":"sakti","year":"2008","journal-title":"Proc Workshop Technol Corpora Asia–Pacific Speech Transl (TCAST)"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICEECS.2014.7045217"},{"key":"ref5","first-page":"264","article-title":"Sphin$\\times4$ for Indonesian continuous speech recognition system","author":"muljono","year":"2017","journal-title":"Proc Int Seminar Appl Technol Inf Commun (ISemantic)"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1566\/1\/012118"},{"key":"ref7","first-page":"67","article-title":"A GrAF-compliant Indonesian speech recognition Web service on the language grid for transcription crowdsourcing","author":"distiawan","year":"2012","journal-title":"Proc 6th Linguistic Annotation Workshop"},{"journal-title":"tvOneNews","year":"2020","key":"ref49"},{"key":"ref9","first-page":"1291","article-title":"Speech recognition on Indonesian language by using time delay neural network","author":"atmaja","year":"2018","journal-title":"Proc ASJ Spring Meet"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"article-title":"Phoneme vs grapheme based automatic speech recognition","year":"2004","author":"magimai-doss","key":"ref45"},{"journal-title":"Metrotvnews","year":"2020","key":"ref48"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683745"},{"key":"ref42","first-page":"1863","article-title":"A clockwork RNN","author":"koutnik","year":"2014","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref44","first-page":"1","article-title":"Revising perceptual linear prediction (PLP)","author":"h\u00f6nig","year":"2005","journal-title":"Proc 9th Eur Conf Speech Commun Technol"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICAIIT.2019.8834514"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09422689.pdf?arnumber=9422689","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T10:11:51Z","timestamp":1672049511000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9422689\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3077441","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2021]]}}}