{"id":"https://openalex.org/W7130332844","doi":"https://doi.org/10.1109/o-cocosda68185.2025.11385168","title":"Accent Conversion: Preserving Speaker Identity in Native English Synthesis","display_name":"Accent Conversion: Preserving Speaker Identity in Native English Synthesis","publication_year":2025,"publication_date":"2025-11-12","ids":{"openalex":"https://openalex.org/W7130332844","doi":"https://doi.org/10.1109/o-cocosda68185.2025.11385168"},"language":null,"primary_location":{"id":"doi:10.1109/o-cocosda68185.2025.11385168","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda68185.2025.11385168","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 28th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5083665711","display_name":"Sabyasachi Chandra","orcid":"https://orcid.org/0009-0003-3051-247X"},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sabyasachi Chandra","raw_affiliation_strings":["Advance Technology Development Centre, Indian Institute of Technology Kharagpur,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advance Technology Development Centre, Indian Institute of Technology Kharagpur,India","institution_ids":["https://openalex.org/I145894827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044762857","display_name":"Puja Bharati","orcid":"https://orcid.org/0009-0000-3468-623X"},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Puja Bharati","raw_affiliation_strings":["Advance Technology Development Centre, Indian Institute of Technology Kharagpur,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advance Technology Development Centre, Indian Institute of Technology Kharagpur,India","institution_ids":["https://openalex.org/I145894827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026317147","display_name":"Debolina Pramanik","orcid":"https://orcid.org/0009-0004-2170-4450"},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Debolina Pramanik","raw_affiliation_strings":["Advance Technology Development Centre, Indian Institute of Technology Kharagpur,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advance Technology Development Centre, Indian Institute of Technology Kharagpur,India","institution_ids":["https://openalex.org/I145894827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103503442","display_name":"Shyamal Kumar Das Mandal","orcid":null},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shyamal Kumar Das Mandal","raw_affiliation_strings":["Advance Technology Development Centre, Indian Institute of Technology Kharagpur,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advance Technology Development Centre, Indian Institute of Technology Kharagpur,India","institution_ids":["https://openalex.org/I145894827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126298261","display_name":"Riya Sil","orcid":null},"institutions":[{"id":"https://openalex.org/I74786994","display_name":"Kitware (United States)","ror":"https://ror.org/02s2acn37","country_code":"US","type":"company","lineage":["https://openalex.org/I74786994"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Riya Sil","raw_affiliation_strings":["Brainware University,Department of Computer Science &amp; Engineering,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brainware University,Department of Computer Science &amp; Engineering,India","institution_ids":["https://openalex.org/I74786994"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.68382163,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.6539999842643738,"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":0.6539999842643738,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.09350000321865082,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.062300000339746475,"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/stress","display_name":"Stress (linguistics)","score":0.6840999722480774},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.46560001373291016},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.367000013589859},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.34779998660087585},{"id":"https://openalex.org/keywords/immediacy","display_name":"Immediacy","score":0.33340001106262207},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.32739999890327454}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6934000253677368},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.6840999722480774},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.618399977684021},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48649999499320984},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.46560001373291016},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4611000120639801},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.40389999747276306},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.367000013589859},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.34779998660087585},{"id":"https://openalex.org/C2780340563","wikidata":"https://www.wikidata.org/wiki/Q2811064","display_name":"Immediacy","level":2,"score":0.33340001106262207},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.32739999890327454},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.30979999899864197},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.28040000796318054},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.25929999351501465}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/o-cocosda68185.2025.11385168","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda68185.2025.11385168","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 28th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6968614459037781}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2143076222","https://openalex.org/W2798685342","https://openalex.org/W2949650786","https://openalex.org/W2973142754","https://openalex.org/W2996414377","https://openalex.org/W3204009030"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"an":[3,33,84],"advanced":[4],"system":[5,42,115],"for":[6,79,131],"Accent":[7,34],"Conversion":[8,39],"(AC)":[9],"that":[10],"enhances":[11],"the":[12,25],"transformation":[13],"of":[14,69,91],"nonnative":[15],"English":[16,95],"speech":[17],"to":[18],"a":[19,30,37,88,128],"native-accented":[20,57],"equivalent":[21],"while":[22],"meticulously":[23],"preserving":[24],"speaker's":[26],"unique":[27],"identity.":[28],"Integrating":[29],"Speaker":[31],"Encoder,":[32,35],"and":[36,59,93,103,122],"Voice":[38],"model,":[40],"our":[41,65,97],"enables":[43],"real-time":[44],"accent":[45,80,111],"conversion":[46],"with":[47],"minimal":[48],"processing":[49,63],"delays.":[50],"Unlike":[51],"traditional":[52],"AC":[53],"methods":[54],"which":[55],"require":[56],"input":[58],"suffer":[60],"from":[61],"lengthy":[62],"times,":[64],"approach":[66],"operates":[67],"independently":[68],"native":[70,94,110],"utterances,":[71],"leveraging":[72],"recent":[73],"advances":[74],"in":[75],"speaker-independent":[76],"phonetic":[77,102],"posteriorgrams":[78],"conversion.":[81],"Trained":[82],"on":[83],"extensive":[85],"dataset":[86],"encompassing":[87],"diverse":[89],"range":[90],"non-native":[92],"accents,":[96],"model":[98],"proficiently":[99],"captures":[100],"intricate":[101],"prosodic":[104],"nuances,":[105],"thus":[106],"facilitating":[107],"highly":[108],"accurate":[109],"synthesis.":[112],"The":[113],"proposed":[114],"is":[116],"distinguished":[117],"by":[118],"its":[119],"operational":[120],"immediacy":[121],"reduced":[123],"computational":[124],"demands,":[125],"rendering":[126],"it":[127],"viable":[129],"solution":[130],"immediate":[132],"application":[133],"scenarios.":[134]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-02-19T00:00:00"}
