{"id":"https://openalex.org/W4413700826","doi":"https://doi.org/10.1007/s10791-025-09701-3","title":"Advancing Bangla text-to-speech synthesis using a VITS-based model with a custom dataset and comprehensive evaluation","display_name":"Advancing Bangla text-to-speech synthesis using a VITS-based model with a custom dataset and comprehensive evaluation","publication_year":2025,"publication_date":"2025-08-26","ids":{"openalex":"https://openalex.org/W4413700826","doi":"https://doi.org/10.1007/s10791-025-09701-3"},"language":"en","primary_location":{"id":"doi:10.1007/s10791-025-09701-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10791-025-09701-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10791-025-09701-3.pdf","source":{"id":"https://openalex.org/S5407036663","display_name":"Discover Computing","issn_l":"2948-2992","issn":["2948-2992"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Discover Computing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://link.springer.com/content/pdf/10.1007/s10791-025-09701-3.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101011415","display_name":"Sujeet Kumar","orcid":"https://orcid.org/0009-0007-6912-9418"},"institutions":[{"id":"https://openalex.org/I4210162014","display_name":"Indian Institute of Management Ranchi","ror":"https://ror.org/05t1d6r64","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210162014"]},{"id":"https://openalex.org/I99552915","display_name":"University of Rajasthan","ror":"https://ror.org/05arfhc56","country_code":"IN","type":"education","lineage":["https://openalex.org/I99552915"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Sujeet Kumar","raw_affiliation_strings":["Indian Institute of Information Technology Ranchi, Jharkhand, 835217, Ranchi, India","Manipal University Jaipur, Rajasthan, 303007, Jaipur, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Information Technology Ranchi, Jharkhand, 835217, Ranchi, India","institution_ids":["https://openalex.org/I4210162014"]},{"raw_affiliation_string":"Manipal University Jaipur, Rajasthan, 303007, Jaipur, India","institution_ids":["https://openalex.org/I99552915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088545260","display_name":"Siddharth Kumar","orcid":"https://orcid.org/0000-0002-2548-1520"},"institutions":[{"id":"https://openalex.org/I4210162014","display_name":"Indian Institute of Management Ranchi","ror":"https://ror.org/05t1d6r64","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210162014"]},{"id":"https://openalex.org/I99552915","display_name":"University of Rajasthan","ror":"https://ror.org/05arfhc56","country_code":"IN","type":"education","lineage":["https://openalex.org/I99552915"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Siddharth Kumar","raw_affiliation_strings":["Indian Institute of Information Technology Ranchi, Jharkhand, 835217, Ranchi, India","Manipal University Jaipur, Rajasthan, 303007, Jaipur, India"],"raw_orcid":"https://orcid.org/0000-0002-2548-1520","affiliations":[{"raw_affiliation_string":"Indian Institute of Information Technology Ranchi, Jharkhand, 835217, Ranchi, India","institution_ids":["https://openalex.org/I4210162014"]},{"raw_affiliation_string":"Manipal University Jaipur, Rajasthan, 303007, Jaipur, India","institution_ids":["https://openalex.org/I99552915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119440873","display_name":"Kushal Sathe","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153931","display_name":"D.Y. Patil University","ror":"https://ror.org/045qb5273","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210153931"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Kushal Sathe","raw_affiliation_strings":["Ajeenkya DY Patil School of Engineering, Pune, 412105, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ajeenkya DY Patil School of Engineering, Pune, 412105, India","institution_ids":["https://openalex.org/I4210153931"]}]},{"author_position":"last","author":{"id":null,"display_name":"Jayadeep Pati","orcid":"https://orcid.org/0000-0003-4348-073X"},"institutions":[{"id":"https://openalex.org/I4210162014","display_name":"Indian Institute of Management Ranchi","ror":"https://ror.org/05t1d6r64","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210162014"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Jayadeep Pati","raw_affiliation_strings":["Indian Institute of Information Technology Ranchi, Jharkhand, 835217, Ranchi, India"],"raw_orcid":"https://orcid.org/0000-0003-4348-073X","affiliations":[{"raw_affiliation_string":"Indian Institute of Information Technology Ranchi, Jharkhand, 835217, Ranchi, India","institution_ids":["https://openalex.org/I4210162014"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101011415"],"corresponding_institution_ids":["https://openalex.org/I4210162014","https://openalex.org/I99552915"],"apc_list":null,"apc_paid":null,"fwci":2.0776,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.89745586,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"28","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9990000128746033,"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/T10860","display_name":"Speech and Audio Processing","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/bengali","display_name":"Bengali","score":0.9027507901191711},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6607786417007446},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6183551549911499},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5501964688301086},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47936302423477173},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.32698357105255127}],"concepts":[{"id":"https://openalex.org/C19235068","wikidata":"https://www.wikidata.org/wiki/Q9610","display_name":"Bengali","level":2,"score":0.9027507901191711},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6607786417007446},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6183551549911499},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5501964688301086},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47936302423477173},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.32698357105255127}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s10791-025-09701-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10791-025-09701-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10791-025-09701-3.pdf","source":{"id":"https://openalex.org/S5407036663","display_name":"Discover Computing","issn_l":"2948-2992","issn":["2948-2992"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Discover Computing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:1bc5b3a0a8674f2a8bebcc9308a5f3bc","is_oa":true,"landing_page_url":"https://doaj.org/article/1bc5b3a0a8674f2a8bebcc9308a5f3bc","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Discover Computing, Vol 28, Iss 1, Pp 1-23 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s10791-025-09701-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10791-025-09701-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10791-025-09701-3.pdf","source":{"id":"https://openalex.org/S5407036663","display_name":"Discover Computing","issn_l":"2948-2992","issn":["2948-2992"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Discover Computing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4413700826.pdf","grobid_xml":"https://content.openalex.org/works/W4413700826.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W1995565802","https://openalex.org/W2107860279","https://openalex.org/W2134973740","https://openalex.org/W2150658333","https://openalex.org/W2518345121","https://openalex.org/W2962691331","https://openalex.org/W2963154580","https://openalex.org/W2963609956","https://openalex.org/W2968203043","https://openalex.org/W2990138404","https://openalex.org/W3021620182","https://openalex.org/W3144035034","https://openalex.org/W3201199308","https://openalex.org/W4221166168","https://openalex.org/W4301420498","https://openalex.org/W4312685746"],"related_works":["https://openalex.org/W2084490135","https://openalex.org/W4298170800","https://openalex.org/W2895890526","https://openalex.org/W617692174","https://openalex.org/W2794758919","https://openalex.org/W4232781930","https://openalex.org/W2028401451","https://openalex.org/W2769530083","https://openalex.org/W3161006337","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Bangla":[0,21,82,139,164,170],"(Bengali)":[1],"voice":[2],"synthesis":[3],"presents":[4],"distinct":[5],"issues":[6],"due":[7],"to":[8,67,105,124,134,161],"its":[9],"restricted":[10],"language":[11,41],"resources":[12],"and":[13,114,116,141,173,183],"complex":[14,153],"vocabulary.":[15,154],"This":[16,78,198],"work":[17],"introduces":[18,80],"a":[19,44,53,81,91,98,107,117],"state-of-the-art":[20],"text-to-speech":[22,206],"(TTS)":[23,207],"system":[24,84],"that":[25,192],"utilizes":[26],"the":[27,39,130,178,193,201],"Variational":[28],"Inference":[29],"Synthesis":[30],"of":[31,49,96,122,181],"Speech":[32],"(VITS)":[33],"architecture.":[34],"We":[35],"tailor":[36],"VITS":[37],"for":[38],"Bengali":[40],"by":[42],"utilizing":[43],"20-hour":[45],"custom-made":[46],"dataset":[47],"consisting":[48],"speech":[50,194],"samples":[51],"from":[52,56,103],"single":[54],"speaker":[55],"native":[57],"literary":[58],"works.":[59],"The":[60,155],"model":[61,144,156],"undergoes":[62],"comprehensive":[63],"training,":[64],"enabling":[65],"it":[66],"convert":[68],"text":[69],"into":[70],"waveforms":[71],"while":[72],"detecting":[73],"subtle":[74],"pronunciation":[75],"variations":[76],"accurately.":[77],"study":[79,199],"TTS":[83,140,165],"based":[85],"on":[86],"VITS,":[87],"which":[88,209],"has":[89,157],"attained":[90],"Mean":[92],"Opinion":[93],"Score":[94],"(MOS)":[95],"4.01,":[97],"Mel-Cepstral":[99],"Distortion":[100],"(MCD)":[101],"ranging":[102],"5.24":[104],"5.48,":[106],"Word":[108],"Error":[109,119],"Rate":[110,120],"(WER)":[111],"between":[112],"0.16":[113],"0.18,":[115],"Phoneme":[118],"(PER)":[121],"0.15":[123],"0.17.":[125],"These":[126],"performance":[127,160],"indicators":[128],"validate":[129,177],"system\u2019s":[131],"excellence":[132],"compared":[133],"current":[135,202],"alternatives":[136],"like":[137],"Google":[138,169],"Narakeet.":[142],"Our":[143],"exhibits":[145],"strong":[146],"generalization":[147],"capabilities,":[148],"particularly":[149],"with":[150],"previously":[151],"unseen":[152],"demonstrated":[158],"superior":[159],"publicly":[162],"accessible":[163],"models":[166],"such":[167],"as":[168],"TTS,":[171],"Narakeet,":[172],"AI4Bharat.":[174],"Objective":[175],"metrics":[176],"high":[179],"level":[180],"comprehensibility":[182],"resemblance":[184],"among":[185],"speakers.":[186],"Preliminary":[187],"informal":[188],"hearing":[189],"tests":[190],"indicate":[191],"sounds":[195],"highly":[196],"natural.":[197],"demonstrates":[200],"advancements":[203],"in":[204,213],"neural":[205],"technology,":[208],"can":[210],"be":[211],"used":[212],"low-resource":[214],"Indian":[215],"languages,":[216],"provided":[217],"sufficient":[218],"data":[219],"is":[220],"available.":[221]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}
