{"id":"https://openalex.org/W4405633700","doi":"https://doi.org/10.1109/o-cocosda64382.2024.10800714","title":"An Evaluation of Neural Vocoder-Based Voice Cloning System for Dysphonia Speech Disorder","display_name":"An Evaluation of Neural Vocoder-Based Voice Cloning System for Dysphonia Speech Disorder","publication_year":2024,"publication_date":"2024-10-17","ids":{"openalex":"https://openalex.org/W4405633700","doi":"https://doi.org/10.1109/o-cocosda64382.2024.10800714"},"language":"en","primary_location":{"id":"doi:10.1109/o-cocosda64382.2024.10800714","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda64382.2024.10800714","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 27th 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":"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/A5115563295","display_name":"Dhiya Dewangga","orcid":null},"institutions":[{"id":"https://openalex.org/I134635517","display_name":"Bandung Institute of Technology","ror":"https://ror.org/00apj8t60","country_code":"ID","type":"education","lineage":["https://openalex.org/I134635517"]}],"countries":["ID"],"is_corresponding":true,"raw_author_name":"Dhiya Dewangga","raw_affiliation_strings":["Bandung Institute of Technology,Indonesia"],"affiliations":[{"raw_affiliation_string":"Bandung Institute of Technology,Indonesia","institution_ids":["https://openalex.org/I134635517"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109119353","display_name":"Dessi Puji Lestari","orcid":null},"institutions":[{"id":"https://openalex.org/I134635517","display_name":"Bandung Institute of Technology","ror":"https://ror.org/00apj8t60","country_code":"ID","type":"education","lineage":["https://openalex.org/I134635517"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Dessi Lestari","raw_affiliation_strings":["Bandung Institute of Technology,Indonesia"],"affiliations":[{"raw_affiliation_string":"Bandung Institute of Technology,Indonesia","institution_ids":["https://openalex.org/I134635517"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021128017","display_name":"Ayu Purwarianti","orcid":"https://orcid.org/0000-0002-5016-3700"},"institutions":[{"id":"https://openalex.org/I134635517","display_name":"Bandung Institute of Technology","ror":"https://ror.org/00apj8t60","country_code":"ID","type":"education","lineage":["https://openalex.org/I134635517"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Ayu Purwarianti","raw_affiliation_strings":["Bandung Institute of Technology,Indonesia"],"affiliations":[{"raw_affiliation_string":"Bandung Institute of Technology,Indonesia","institution_ids":["https://openalex.org/I134635517"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066930701","display_name":"Dipta Tanaya","orcid":"https://orcid.org/0009-0000-1480-8041"},"institutions":[{"id":"https://openalex.org/I29617571","display_name":"University of Indonesia","ror":"https://ror.org/0116zj450","country_code":"ID","type":"education","lineage":["https://openalex.org/I29617571"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Dipta Tanaya","raw_affiliation_strings":["University of Indonesia,Indonesia"],"affiliations":[{"raw_affiliation_string":"University of Indonesia,Indonesia","institution_ids":["https://openalex.org/I29617571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066073372","display_name":"Kurniawati Azizah","orcid":"https://orcid.org/0000-0002-3217-7025"},"institutions":[{"id":"https://openalex.org/I29617571","display_name":"University of Indonesia","ror":"https://ror.org/0116zj450","country_code":"ID","type":"education","lineage":["https://openalex.org/I29617571"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Kurniawati Azizah","raw_affiliation_strings":["University of Indonesia,Indonesia"],"affiliations":[{"raw_affiliation_string":"University of Indonesia,Indonesia","institution_ids":["https://openalex.org/I29617571"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040108974","display_name":"Sakriani Sakti","orcid":"https://orcid.org/0000-0001-5509-8963"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sakriani Sakti","raw_affiliation_strings":["Nara Institute of Science and Technology,Japan"],"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology,Japan","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5115563295"],"corresponding_institution_ids":["https://openalex.org/I134635517"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33757752,"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":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.9797000288963318,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.9797000288963318,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9602000117301941,"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/speech-recognition","display_name":"Speech recognition","score":0.751887321472168},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7101795673370361},{"id":"https://openalex.org/keywords/cloning","display_name":"Cloning (programming)","score":0.5102789402008057},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.46476539969444275},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4151892066001892},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3869917094707489}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.751887321472168},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7101795673370361},{"id":"https://openalex.org/C121050878","wikidata":"https://www.wikidata.org/wiki/Q5135020","display_name":"Cloning (programming)","level":2,"score":0.5102789402008057},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.46476539969444275},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4151892066001892},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3869917094707489},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/o-cocosda64382.2024.10800714","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda64382.2024.10800714","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 27th 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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W98096188","https://openalex.org/W1558063916","https://openalex.org/W1598514414","https://openalex.org/W2022125261","https://openalex.org/W2038659592","https://openalex.org/W2049612161","https://openalex.org/W2086972305","https://openalex.org/W2116593694","https://openalex.org/W2138830098","https://openalex.org/W2519091744","https://openalex.org/W2523517780","https://openalex.org/W2606849474","https://openalex.org/W2789416342","https://openalex.org/W2798685342","https://openalex.org/W2903739847","https://openalex.org/W2962788625","https://openalex.org/W2964243274","https://openalex.org/W2980242586","https://openalex.org/W2999537907","https://openalex.org/W3015707856","https://openalex.org/W3095790275","https://openalex.org/W3097206152","https://openalex.org/W3097547259","https://openalex.org/W3097881066","https://openalex.org/W4200429098","https://openalex.org/W4282960218","https://openalex.org/W6713967443","https://openalex.org/W6734815144","https://openalex.org/W6748409065","https://openalex.org/W6752888775","https://openalex.org/W6780218876","https://openalex.org/W6783867762","https://openalex.org/W6805710207"],"related_works":["https://openalex.org/W191108438","https://openalex.org/W3135230428","https://openalex.org/W2904739811","https://openalex.org/W249088392","https://openalex.org/W2152158029","https://openalex.org/W2012540220","https://openalex.org/W2131711534","https://openalex.org/W2559040841","https://openalex.org/W114661351","https://openalex.org/W596245619"],"abstract_inverted_index":{"Dysphonia":[0,18],"is":[1,82],"a":[2,102],"voice":[3,6,90,103],"disorder":[4],"affecting":[5],"quality,":[7],"quantity,":[8],"and":[9,15,54,123],"intensity,":[10],"occurring":[11],"at":[12],"various":[13,72],"ages":[14],"diverse":[16],"backgrounds.":[17],"impacts":[19],"the":[20,26,38,96,99,107,128,135,147,150],"difficulty":[21],"of":[22,29,41,69,98,109,130,149],"communication,":[23],"thereby":[24],"reducing":[25],"overall":[27],"quality":[28,40,108,148],"life.":[30],"Medical":[31],"solutions":[32,47,59],"have":[33],"been":[34],"proposed":[35,76],"to":[36,62,145],"improve":[37],"speech":[39,64,83,111],"individuals":[42],"with":[43,89],"dysphonia.":[44],"However,":[45],"these":[46],"are":[48,60],"often":[49],"limited":[50],"by":[51],"considerable":[52],"expenses":[53],"time-consuming":[55],"procedures.":[56],"Therefore,":[57],"alternative":[58,79],"needed":[61],"enhance":[63],"quality.":[65],"The":[66],"widespread":[67],"development":[68],"technology":[70,85],"in":[71,101],"domains":[73],"can":[74],"be":[75],"as":[77],"an":[78,139],"solution.":[80],"One":[81],"processing":[84],"using":[86,131],"text-to-speech":[87],"(TTS)":[88],"cloning":[91,104],"techniques.":[92],"Our":[93],"work":[94],"presents":[95],"impact":[97],"vocoder":[100,118,144],"system":[105],"on":[106,121,134],"synthesized":[110],"for":[112,142],"dysphonia":[113],"speakers.":[114],"We":[115,137],"compare":[116],"selected":[117],"models":[119],"based":[120],"architecture":[122],"performance.":[124],"Furthermore,":[125],"we":[126],"explore":[127],"effect":[129],"Speaker":[132],"Conditionals":[133],"vocoder.":[136],"perform":[138],"objective":[140],"evaluation":[141],"each":[143],"measure":[146],"models.":[151]},"counts_by_year":[],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}