{"id":"https://openalex.org/W4406461854","doi":"https://doi.org/10.1109/bigdata62323.2024.10826131","title":"BanglaDialecto: An End-to-End AI-Powered Regional Speech Standardization","display_name":"BanglaDialecto: An End-to-End AI-Powered Regional Speech Standardization","publication_year":2024,"publication_date":"2024-12-15","ids":{"openalex":"https://openalex.org/W4406461854","doi":"https://doi.org/10.1109/bigdata62323.2024.10826131"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata62323.2024.10826131","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10826131","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114730206","display_name":"Md. Nazmus Sadat Samin","orcid":null},"institutions":[{"id":"https://openalex.org/I157386601","display_name":"North South University","ror":"https://ror.org/05wdbfp45","country_code":"BD","type":"education","lineage":["https://openalex.org/I157386601"]}],"countries":["BD"],"is_corresponding":true,"raw_author_name":"Md. Nazmus Sadat Samin","raw_affiliation_strings":["ECE North South University,Apurba-NSU R&#x0026;D Lab,Dhaka,Bangladesh"],"affiliations":[{"raw_affiliation_string":"ECE North South University,Apurba-NSU R&#x0026;D Lab,Dhaka,Bangladesh","institution_ids":["https://openalex.org/I157386601"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114730207","display_name":"Jawad Ibn Ahad","orcid":"https://orcid.org/0009-0000-1383-7756"},"institutions":[{"id":"https://openalex.org/I157386601","display_name":"North South University","ror":"https://ror.org/05wdbfp45","country_code":"BD","type":"education","lineage":["https://openalex.org/I157386601"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Jawad Ibn Ahad","raw_affiliation_strings":["ECE North South University,Apurba-NSU R&#x0026;D Lab,Dhaka,Bangladesh"],"affiliations":[{"raw_affiliation_string":"ECE North South University,Apurba-NSU R&#x0026;D Lab,Dhaka,Bangladesh","institution_ids":["https://openalex.org/I157386601"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114730208","display_name":"Tanjila Ahmed Medha","orcid":null},"institutions":[{"id":"https://openalex.org/I157386601","display_name":"North South University","ror":"https://ror.org/05wdbfp45","country_code":"BD","type":"education","lineage":["https://openalex.org/I157386601"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Tanjila Ahmed Medha","raw_affiliation_strings":["ECE North South University,Apurba-NSU R&#x0026;D Lab,Dhaka,Bangladesh"],"affiliations":[{"raw_affiliation_string":"ECE North South University,Apurba-NSU R&#x0026;D Lab,Dhaka,Bangladesh","institution_ids":["https://openalex.org/I157386601"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112723412","display_name":"Fuad Rahman","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fuad Rahman","raw_affiliation_strings":["Apurba Technologies,Sunnyvale,CA,USA,94085"],"affiliations":[{"raw_affiliation_string":"Apurba Technologies,Sunnyvale,CA,USA,94085","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028396045","display_name":"Mohammad Ruhul Amin","orcid":"https://orcid.org/0000-0001-6540-3415"},"institutions":[{"id":"https://openalex.org/I164389053","display_name":"Fordham University","ror":"https://ror.org/03qnxaf80","country_code":"US","type":"education","lineage":["https://openalex.org/I164389053"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammad Ruhul Amin","raw_affiliation_strings":["Fordham University,Computer and Information Science,New York,USA"],"affiliations":[{"raw_affiliation_string":"Fordham University,Computer and Information Science,New York,USA","institution_ids":["https://openalex.org/I164389053"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062072064","display_name":"Nabeel Mohammed","orcid":"https://orcid.org/0000-0002-7661-3570"},"institutions":[{"id":"https://openalex.org/I157386601","display_name":"North South University","ror":"https://ror.org/05wdbfp45","country_code":"BD","type":"education","lineage":["https://openalex.org/I157386601"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Nabeel Mohammed","raw_affiliation_strings":["ECE North South University,Apurba-NSU R&#x0026;D Lab,Dhaka,Bangladesh"],"affiliations":[{"raw_affiliation_string":"ECE North South University,Apurba-NSU R&#x0026;D Lab,Dhaka,Bangladesh","institution_ids":["https://openalex.org/I157386601"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007895165","display_name":"Shafin Rahman","orcid":"https://orcid.org/0000-0001-7169-0318"},"institutions":[{"id":"https://openalex.org/I157386601","display_name":"North South University","ror":"https://ror.org/05wdbfp45","country_code":"BD","type":"education","lineage":["https://openalex.org/I157386601"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Shafin Rahman","raw_affiliation_strings":["ECE North South University,Apurba-NSU R&#x0026;D Lab,Dhaka,Bangladesh"],"affiliations":[{"raw_affiliation_string":"ECE North South University,Apurba-NSU R&#x0026;D Lab,Dhaka,Bangladesh","institution_ids":["https://openalex.org/I157386601"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5114730206"],"corresponding_institution_ids":["https://openalex.org/I157386601"],"apc_list":null,"apc_paid":null,"fwci":0.6891,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.77771629,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1635","last_page":"1644"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.991599977016449,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.8744494318962097},{"id":"https://openalex.org/keywords/standardization","display_name":"Standardization","score":0.8704339861869812},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6371150016784668},{"id":"https://openalex.org/keywords/end-user","display_name":"End user","score":0.4330790638923645},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.37365081906318665},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2038816213607788},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.14611104130744934},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.08138588070869446}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.8744494318962097},{"id":"https://openalex.org/C188087704","wikidata":"https://www.wikidata.org/wiki/Q369577","display_name":"Standardization","level":2,"score":0.8704339861869812},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6371150016784668},{"id":"https://openalex.org/C91262260","wikidata":"https://www.wikidata.org/wiki/Q528074","display_name":"End user","level":2,"score":0.4330790638923645},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37365081906318665},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2038816213607788},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.14611104130744934},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.08138588070869446}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata62323.2024.10826131","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10826131","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W1910131649","https://openalex.org/W1922655562","https://openalex.org/W2101105183","https://openalex.org/W2133119840","https://openalex.org/W2221014852","https://openalex.org/W2834996597","https://openalex.org/W2891336433","https://openalex.org/W2895411524","https://openalex.org/W2896457183","https://openalex.org/W2899663614","https://openalex.org/W2939451971","https://openalex.org/W2970252335","https://openalex.org/W2981022124","https://openalex.org/W3012217511","https://openalex.org/W3016136182","https://openalex.org/W3021620182","https://openalex.org/W3033801201","https://openalex.org/W3097341038","https://openalex.org/W3097847448","https://openalex.org/W3169483174","https://openalex.org/W3170852415","https://openalex.org/W3173069567","https://openalex.org/W3185689807","https://openalex.org/W3198887975","https://openalex.org/W3214292156","https://openalex.org/W4205278983","https://openalex.org/W4226278482","https://openalex.org/W4283755617","https://openalex.org/W4285273143","https://openalex.org/W4301581299","https://openalex.org/W4307922498","https://openalex.org/W4311000453","https://openalex.org/W4312107650","https://openalex.org/W4312187715","https://openalex.org/W4322732039","https://openalex.org/W4378551677","https://openalex.org/W4381463374","https://openalex.org/W4384389802","https://openalex.org/W4386185396","https://openalex.org/W4386566460","https://openalex.org/W4388890969","https://openalex.org/W4391420283","https://openalex.org/W4392355216","https://openalex.org/W4395462509","https://openalex.org/W4399265137","https://openalex.org/W4399912074","https://openalex.org/W4401042993","https://openalex.org/W4402090665","https://openalex.org/W6628767913","https://openalex.org/W6640090968","https://openalex.org/W6755207826","https://openalex.org/W6755977528","https://openalex.org/W6773820404","https://openalex.org/W6784577980","https://openalex.org/W6839396370","https://openalex.org/W6847363464","https://openalex.org/W6847709088","https://openalex.org/W6854475153","https://openalex.org/W6856168926","https://openalex.org/W6858635353","https://openalex.org/W6869586954","https://openalex.org/W6882690161","https://openalex.org/W7036876807"],"related_works":["https://openalex.org/W4299590256","https://openalex.org/W2151749779","https://openalex.org/W4404782863","https://openalex.org/W3163634122","https://openalex.org/W2110442089","https://openalex.org/W2166381389","https://openalex.org/W4315785295","https://openalex.org/W4393280045","https://openalex.org/W2054736184","https://openalex.org/W3159728998"],"abstract_inverted_index":{"This":[0,158,173],"study":[1,159],"focuses":[2],"on":[3],"recognizing":[4],"Bangladeshi":[5],"dialects":[6,96,104],"and":[7,35,42,48,58,76,123,154,192,202,225],"converting":[8,165],"diverse":[9,128,179],"Bengali":[10,15],"accents":[11],"into":[12,272],"standardized":[13],"formal":[14],"speech.":[16,172],"Dialects,":[17],"often":[18],"referred":[19],"to":[20,65,72,117,144,169,199,207],"as":[21],"regional":[22],"languages,":[23],"are":[24,36,50],"distinctive":[25],"variations":[26],"of":[27,79,120,126,148,223,227,237],"a":[28,32,118,177,221,234,254],"language":[29,91],"spoken":[30,90,97],"in":[31,46,133,190],"particular":[33],"location":[34],"identified":[37],"by":[38,53,98,251],"their":[39],"phonetics,":[40],"pronunciations,":[41],"lexicon.":[43],"Subtle":[44],"changes":[45],"pronunciation":[47],"intonation":[49],"also":[51],"influenced":[52],"geographic":[54],"location,":[55],"educational":[56,69],"attainment,":[57],"socioeconomic":[59],"status.":[60],"Dialect":[61],"standardization":[62,250],"is":[63,105],"needed":[64],"ensure":[66],"effective":[67],"communication,":[68],"consistency,":[70],"access":[71],"technology,":[73],"economic":[74],"opportunities,":[75],"the":[77,87,124,131,146,187,196,204,216,230,267],"preservation":[78],"linguistic":[80],"resources":[81],"while":[82,229],"respecting":[83],"cultural":[84],"diversity.":[85],"Being":[86],"fifth":[88],"most":[89],"with":[92,181],"around":[93],"55":[94],"distinct":[95],"160":[99],"million":[100],"people,":[101],"addressing":[102],"Bangla":[103,171,209,273],"crucial":[106],"for":[107,164,194,239,248,269],"developing":[108],"inclusive":[109],"communication":[110],"tools.":[111],"However,":[112],"limited":[113],"research":[114,265,271],"exists":[115],"due":[116],"lack":[119],"comprehensive":[121],"datasets":[122],"challenges":[125,147],"handling":[127],"dialects.":[129],"With":[130,258],"advancement":[132],"multilingual":[134],"Large":[135],"Language":[136],"Models":[137],"(mLLMs),":[138],"emerging":[139],"possibilities":[140],"have":[141],"been":[142],"created":[143],"address":[145],"dialectal":[149,166,182],"Automated":[150],"Speech":[151],"Recognition":[152],"(ASR)":[153],"Machine":[155],"Translation":[156],"(MT).":[157],"presents":[160],"an":[161],"end-to-end":[162,246],"pipeline":[163,247],"Noakhali":[167],"speech":[168,183,198],"standard":[170,208],"investigation":[174],"includes":[175],"constructing":[176],"large-scale":[178],"dataset":[180],"signals":[184],"that":[185,214],"tailored":[186],"fine-tuning":[188,215],"process":[189],"ASR":[191,218],"LLM":[193],"transcribing":[195],"dialect":[197,200,205,249,274],"text":[201,206,241],"translating":[203],"text.":[210],"Our":[211],"experiments":[212],"demonstrated":[213],"Whisper":[217],"model":[219,232],"achieved":[220],"CER":[222],"0.8%":[224],"WER":[226],"1.5%,":[228],"BanglaT5":[231],"attained":[233],"BLEU":[235],"score":[236],"41.6%":[238],"dialect-to-standard":[240],"translation.":[242],"We":[243],"completed":[244],"our":[245],"utilizing":[252],"AlignTTS,":[253],"text-to-speech":[255],"(TTS)":[256],"model.":[257],"potential":[259],"applications":[260],"across":[261],"different":[262],"dialects,":[263],"this":[264],"lays":[266],"groundwork":[268],"future":[270],"standardization.":[275]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}
