{"id":"https://openalex.org/W4319862272","doi":"https://doi.org/10.1109/slt54892.2023.10023072","title":"Learning Accent Representation with Multi-Level VAE Towards Controllable Speech Synthesis","display_name":"Learning Accent Representation with Multi-Level VAE Towards Controllable Speech Synthesis","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862272","doi":"https://doi.org/10.1109/slt54892.2023.10023072"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10023072","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10023072","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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/A5051181804","display_name":"Jan Melechovsk\u00fd","orcid":"https://orcid.org/0009-0000-2565-2599"},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jan Melechovsky","raw_affiliation_strings":["Singapore University of Technology and Design"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore University of Technology and Design","institution_ids":["https://openalex.org/I152815399"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065572305","display_name":"Ambuj Mehrish","orcid":"https://orcid.org/0000-0003-4240-9915"},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ambuj Mehrish","raw_affiliation_strings":["Singapore University of Technology and Design"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore University of Technology and Design","institution_ids":["https://openalex.org/I152815399"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069548004","display_name":"Dorien Herremans","orcid":"https://orcid.org/0000-0001-8607-1640"},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Dorien Herremans","raw_affiliation_strings":["Singapore University of Technology and Design"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore University of Technology and Design","institution_ids":["https://openalex.org/I152815399"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001303929","display_name":"Berrak \u015ei\u015fman","orcid":"https://orcid.org/0000-0001-8078-3305"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Berrak Sisman","raw_affiliation_strings":["University of Texas at Dallas"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Dallas","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5245,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.84124336,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"928","last_page":"935"},"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/T12031","display_name":"Speech and dialogue systems","score":0.9930999875068665,"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/T10863","display_name":"Voice and Speech Disorders","score":0.9926999807357788,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.8335255980491638},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7913649678230286},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.7668431401252747},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6223430037498474},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5713478922843933},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.5548570156097412},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.46975114941596985},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.4610210359096527},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.45761552453041077},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4574640393257141},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4410390853881836},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.43158185482025146},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3855572044849396},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3422468602657318},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.12357214093208313},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.07939931750297546}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8335255980491638},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7913649678230286},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.7668431401252747},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6223430037498474},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5713478922843933},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.5548570156097412},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.46975114941596985},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.4610210359096527},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.45761552453041077},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4574640393257141},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4410390853881836},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.43158185482025146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3855572044849396},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3422468602657318},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.12357214093208313},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.07939931750297546},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/slt54892.2023.10023072","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10023072","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},{"id":"pmh:oai:iris.unive.it:10278/5105953","is_oa":false,"landing_page_url":"https://hdl.handle.net/10278/5105953","pdf_url":null,"source":{"id":"https://openalex.org/S4306402336","display_name":"ARCA (Universit\u00e0 Ca' Foscari Venezia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149461666","host_organization_name":"Ca' Foscari University of Venice","host_organization_lineage":["https://openalex.org/I149461666"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5600000023841858,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W602213632","https://openalex.org/W659550629","https://openalex.org/W1991682319","https://openalex.org/W2107860279","https://openalex.org/W2120605154","https://openalex.org/W2124331435","https://openalex.org/W2133564696","https://openalex.org/W2143076222","https://openalex.org/W2157259375","https://openalex.org/W2396366106","https://openalex.org/W2518172956","https://openalex.org/W2519091744","https://openalex.org/W2620364083","https://openalex.org/W2888954148","https://openalex.org/W2904459034","https://openalex.org/W2946200149","https://openalex.org/W2963223306","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W2981087920","https://openalex.org/W2998572311","https://openalex.org/W3033411150","https://openalex.org/W3123665557","https://openalex.org/W3135654121","https://openalex.org/W3151292345","https://openalex.org/W3160329778","https://openalex.org/W3160475509","https://openalex.org/W3175161143","https://openalex.org/W3178546316","https://openalex.org/W3197530164","https://openalex.org/W3197561413","https://openalex.org/W3198791321","https://openalex.org/W3204009030","https://openalex.org/W4243859118","https://openalex.org/W4292387508","https://openalex.org/W4301523212","https://openalex.org/W6603838645","https://openalex.org/W6679434410","https://openalex.org/W6687566353","https://openalex.org/W6688384872","https://openalex.org/W6712235671","https://openalex.org/W6734815144","https://openalex.org/W6749555683","https://openalex.org/W6750489868","https://openalex.org/W6755300632","https://openalex.org/W6763832098","https://openalex.org/W6778823374","https://openalex.org/W6796730497","https://openalex.org/W6801421823"],"related_works":["https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W2108985546","https://openalex.org/W2433276473","https://openalex.org/W1537411440","https://openalex.org/W2024201202","https://openalex.org/W2535215250","https://openalex.org/W2049083033","https://openalex.org/W290673751","https://openalex.org/W2017702615"],"abstract_inverted_index":{"Accent":[0],"is":[1,44,107],"a":[2,64,73,121],"crucial":[3],"aspect":[4],"of":[5,30,48,58],"speech":[6],"that":[7,14,67,127],"helps":[8],"define":[9],"one's":[10],"identity.":[11],"We":[12,109,125],"note":[13],"the":[15,56,111,128],"state-of-the-art":[16],"Text-to-Speech":[17],"(TTS)":[18],"systems":[19],"can":[20,94],"achieve":[21,96],"high-quality":[22,97],"generated":[23],"voice,":[24],"but":[25],"still":[26],"lack":[27],"in":[28,81],"terms":[29],"versatility":[31],"and":[32,77,89,116,138],"customizability.":[33],"Moreover,":[34],"they":[35],"generally":[36],"do":[37],"not":[38],"take":[39],"into":[40],"account":[41],"accent,":[42],"which":[43,104],"an":[45],"important":[46],"feature":[47],"speaking":[49],"style.":[50],"In":[51],"this":[52],"work,":[53],"we":[54,105],"utilize":[55],"concept":[57],"Multi-level":[59],"VAE":[60],"(ML-VAE)":[61],"to":[62,69,78],"build":[63],"control":[65],"mechanism":[66],"aims":[68],"disentangle":[70],"accent":[71,139],"from":[72],"reference":[74],"accented":[75,98],"speaker;":[76],"synthesize":[79],"voices":[80],"different":[82],"accents":[83],"such":[84],"as":[85],"English,":[86],"American,":[87],"Irish,":[88],"Scottish.":[90],"The":[91],"proposed":[92,129],"framework":[93],"also":[95],"voice":[99],"generation":[100],"for":[101,120,134],"multi-speaker":[102],"setup,":[103],"believe":[106],"remarkable.":[108],"investigate":[110],"performance":[112,123,133],"through":[113],"objective":[114],"metrics":[115],"conduct":[117],"listening":[118],"experiments":[119],"subjective":[122],"assessment.":[124],"showed":[126],"method":[130],"achieves":[131],"good":[132],"naturalness,":[135],"speaker":[136],"similarity,":[137],"similarity.":[140]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}