{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T15:17:29Z","timestamp":1784301449383,"version":"3.55.0"},"reference-count":53,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,15]],"date-time":"2024-12-15T00:00:00Z","timestamp":1734220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,15]],"date-time":"2024-12-15T00:00:00Z","timestamp":1734220800000},"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":[[2024,12,15]]},"DOI":"10.1109\/bigdata62323.2024.10826131","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:23Z","timestamp":1737052283000},"page":"1635-1644","source":"Crossref","is-referenced-by-count":4,"title":["BanglaDialecto: An End-to-End AI-Powered Regional Speech Standardization"],"prefix":"10.1109","author":[{"given":"Md. Nazmus","family":"Sadat Samin","sequence":"first","affiliation":[{"name":"ECE North South University,Apurba-NSU R&D Lab,Dhaka,Bangladesh"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jawad","family":"Ibn Ahad","sequence":"additional","affiliation":[{"name":"ECE North South University,Apurba-NSU R&D Lab,Dhaka,Bangladesh"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tanjila Ahmed","family":"Medha","sequence":"additional","affiliation":[{"name":"ECE North South University,Apurba-NSU R&D Lab,Dhaka,Bangladesh"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fuad","family":"Rahman","sequence":"additional","affiliation":[{"name":"Apurba Technologies,Sunnyvale,CA,USA,94085"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohammad Ruhul","family":"Amin","sequence":"additional","affiliation":[{"name":"Fordham University,Computer and Information Science,New York,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nabeel","family":"Mohammed","sequence":"additional","affiliation":[{"name":"ECE North South University,Apurba-NSU R&D Lab,Dhaka,Bangladesh"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shafin","family":"Rahman","sequence":"additional","affiliation":[{"name":"ECE North South University,Apurba-NSU R&D Lab,Dhaka,Bangladesh"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ECACE.2019.8679341"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/SLTU.2018-40"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1250\/ast.42.252"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2639"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.33480\/pilar.v20i1.4633"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-5504-2_18"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.59400\/fls.v6i2.1188"},{"issue":"21","key":"ref8","article-title":"Social factors and dialect variation: An analysis of age, gender, and social class in linguistic practice","author":"Hamed","year":"2023","journal-title":"Refereed Journal of Northern Europe Academy for Studies & Research (Denmark)"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18178\/ijfcc.2020.9.2.564"},{"key":"ref10","article-title":"Vashantor: a large-scale multilingual benchmark dataset for automated translation of bangla regional dialects to bangla language","author":"Faria","year":"2023"},{"key":"ref11","volume-title":"Automatic speech recognition","volume":"1","author":"Yu","year":"2016"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CSII.2018.00016"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2015.69"},{"key":"ref14","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref15","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-024-00349-3"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.176"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3165563"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-023-10668-0"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3177191"},{"key":"ref21","article-title":"End-to-end automatic speech recognition model for the sudanese dialect","author":"Mansour","year":"2022"},{"key":"ref22","article-title":"Deep speech: Scaling up end-to-end speech recognition","author":"Hannun","year":"2014"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2021.05.082"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC47483.2019.9023100"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-19-9483-8_41"},{"key":"ref26","article-title":"Classification of bangla regional languages and recognition of artificial bangla speech using deep learning","volume-title":"Ph.D. dissertation","author":"Hossain","year":"2022"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.56415\/csjm.v31.04"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-eacl.54"},{"key":"ref29","article-title":"mt5: A massively multilingual pre-trained text-to-text transformer","author":"Xue","year":"2020"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TENSYMP50017.2020.9230714"},{"key":"ref31","author":"Alam","year":"2011","journal-title":"Bangla Text to Speech using Festival"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICBSLP47725.2019.202055"},{"key":"ref33","doi-asserted-by":"crossref","DOI":"10.1109\/ICSCT53883.2021.9642672","article-title":"End to end bangla speech synthesis","author":"Bhattacharjee","year":"2021"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-13-0224-4_27"},{"key":"ref35","article-title":"A comprehensive overview of large language models","author":"Naveed","year":"2023"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-018-8030-z"},{"key":"ref37","article-title":"Bengali common voice speech dataset for automatic speech recognition","author":"Alam","year":"2022"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3568674"},{"key":"ref39","article-title":"Automatic speech recognition for biomedical data in bengali language","author":"Kabir","year":"2024"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/MIUCC52538.2021.9447650"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s13369-023-07670-7"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3469721"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICEEI.2015.7352469"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2022.1090012"},{"key":"ref45","article-title":"Sylheti to standard bangla neural machine translation: A deep learning-based dialect conversion approach","author":"Prama"},{"key":"ref46","article-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2022"},{"key":"ref47","article-title":"Gaussian error linear units (gelus)","author":"Hendrycks","year":"2016"},{"key":"ref48","article-title":"Glu variants improve transformer","author":"Shazeer","year":"2020"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054119"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/1188816.1188819"},{"key":"ref51","article-title":"Minimizing word error rate in textual summaries of spoken language","volume-title":"1st Meeting of the North American Chapter of the Association for Computational Linguistics","author":"Zechner"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref53","article-title":"Sparks of large audio models: A survey and outlook","author":"Latif","year":"2023"}],"event":{"name":"2024 IEEE International Conference on Big Data (BigData)","location":"Washington, DC, USA","start":{"date-parts":[[2024,12,15]]},"end":{"date-parts":[[2024,12,18]]}},"container-title":["2024 IEEE International Conference on Big Data (BigData)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10824975\/10824942\/10826131.pdf?arnumber=10826131","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T08:03:23Z","timestamp":1737101003000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10826131\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,15]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/bigdata62323.2024.10826131","relation":{},"subject":[],"published":{"date-parts":[[2024,12,15]]}}}