{"id":"https://openalex.org/W4297841449","doi":"https://doi.org/10.21437/interspeech.2022-10446","title":"Karaoker: Alignment-free singing voice synthesis with speech training data","display_name":"Karaoker: Alignment-free singing voice synthesis with speech training data","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4297841449","doi":"https://doi.org/10.21437/interspeech.2022-10446"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10446","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10446","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","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":null,"display_name":"Panagiotis Kakoulidis","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Panagiotis Kakoulidis","raw_affiliation_strings":["Innoetics, Samsung Electronics, Greece"],"affiliations":[{"raw_affiliation_string":"Innoetics, Samsung Electronics, Greece","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052196585","display_name":"Nikolaos Ellinas","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nikolaos Ellinas","raw_affiliation_strings":["Innoetics, Samsung Electronics, Greece"],"affiliations":[{"raw_affiliation_string":"Innoetics, Samsung Electronics, Greece","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022310876","display_name":"Georgios Vamvoukakis","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Georgios Vamvoukakis","raw_affiliation_strings":["Innoetics, Samsung Electronics, Greece"],"affiliations":[{"raw_affiliation_string":"Innoetics, Samsung Electronics, Greece","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050072052","display_name":"\u039a\u03c9\u03bd\u03c3\u03c4\u03b1\u03bd\u03c4\u03af\u03bd\u03bf\u03c2 \u039c\u03b1\u03c1\u03ba\u03cc\u03c0\u03bf\u03c5\u03bb\u03bf\u03c2","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Konstantinos Markopoulos","raw_affiliation_strings":["Innoetics, Samsung Electronics, Greece"],"affiliations":[{"raw_affiliation_string":"Innoetics, Samsung Electronics, Greece","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110947099","display_name":"June Sig Sung","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"June Sig Sung","raw_affiliation_strings":["Mobile Communications Business, Samsung Electronics, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Mobile Communications Business, Samsung Electronics, Republic of Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041656238","display_name":"Gunu Jho","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Gunu Jho","raw_affiliation_strings":["Mobile Communications Business, Samsung Electronics, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Mobile Communications Business, Samsung Electronics, Republic of Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027494724","display_name":"Pirros Tsiakoulis","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pirros Tsiakoulis","raw_affiliation_strings":["Innoetics, Samsung Electronics, Greece"],"affiliations":[{"raw_affiliation_string":"Innoetics, Samsung Electronics, Greece","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091595884","display_name":"Aimilios Chalamandaris","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aimilios Chalamandaris","raw_affiliation_strings":["Innoetics, Samsung Electronics, Greece"],"affiliations":[{"raw_affiliation_string":"Innoetics, Samsung Electronics, Greece","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3645,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.50991501,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9991000294685364,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9991000294685364,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9988999962806702,"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":0.9941999912261963,"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/singing","display_name":"Singing","score":0.8171169757843018},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8068071603775024},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7967164516448975},{"id":"https://openalex.org/keywords/formant","display_name":"Formant","score":0.6084252595901489},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.46845316886901855},{"id":"https://openalex.org/keywords/human-multitasking","display_name":"Human multitasking","score":0.4361993670463562},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.43579530715942383},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.41930168867111206},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.411003977060318},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38564735651016235},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32455897331237793},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.1930319368839264},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1238129734992981},{"id":"https://openalex.org/keywords/radar","display_name":"Radar","score":0.09667778015136719}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.8171169757843018},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8068071603775024},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7967164516448975},{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.6084252595901489},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.46845316886901855},{"id":"https://openalex.org/C107418235","wikidata":"https://www.wikidata.org/wiki/Q1520565","display_name":"Human multitasking","level":2,"score":0.4361993670463562},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.43579530715942383},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.41930168867111206},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.411003977060318},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38564735651016235},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32455897331237793},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.1930319368839264},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1238129734992981},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.09667778015136719},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-10446","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10446","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5899999737739563,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1875231349","https://openalex.org/W2034995162","https://openalex.org/W2067709094","https://openalex.org/W2128873747","https://openalex.org/W2579593485","https://openalex.org/W2767052532","https://openalex.org/W2890964092","https://openalex.org/W2963300588","https://openalex.org/W2964243274","https://openalex.org/W2972359262","https://openalex.org/W2973046048","https://openalex.org/W3015645837","https://openalex.org/W3095389792","https://openalex.org/W3096086473","https://openalex.org/W3096437652","https://openalex.org/W3101882441","https://openalex.org/W3133525064","https://openalex.org/W3135864795","https://openalex.org/W3160190545","https://openalex.org/W3193323418","https://openalex.org/W3196711362","https://openalex.org/W3197294703","https://openalex.org/W3201257217","https://openalex.org/W3207038517","https://openalex.org/W3215319055","https://openalex.org/W4226154422"],"related_works":["https://openalex.org/W1980770795","https://openalex.org/W2994872662","https://openalex.org/W2053207518","https://openalex.org/W2075905938","https://openalex.org/W2546942002","https://openalex.org/W2062208920","https://openalex.org/W2016461833","https://openalex.org/W3197541072","https://openalex.org/W4224861899","https://openalex.org/W4297841449"],"abstract_inverted_index":{"Existing":[0],"singing":[1,10,53],"voice":[2,38,54],"synthesis":[3],"models":[4],"(SVS)":[5],"are":[6],"usually":[7],"trained":[8,43],"on":[9,14,37,45,82,134],"data":[11,47,84],"and":[12,18,55,93,105],"depend":[13],"either":[15],"error-prone":[16],"time-alignment":[17],"duration":[19],"features":[20,40],"or":[21],"explicit":[22],"music":[23],"score":[24],"information.":[25],"In":[26,117],"this":[27],"paper,":[28],"we":[29,121],"propose":[30],"Karaoker,":[31],"a":[32,59,64,77,124],"multispeaker":[33],"Tacotron-based":[34],"model":[35,72,112],"conditioned":[36,75],"characteristic":[39],"that":[41,109],"is":[42,73],"exclusively":[44],"spoken":[46],"without":[48],"requiring":[49],"time-alignments.":[50],"Karaoker":[51],"synthesizes":[52],"transfers":[56],"style":[57],"following":[58],"multi-dimensional":[60],"template":[61],"extracted":[62],"from":[63],"source":[65],"waveform":[66],"of":[67,144],"an":[68,114],"unseen":[69],"singer/speaker.":[70],"The":[71],"jointly":[74],"with":[76,101],"single":[78],"deep":[79],"convolutional":[80],"encoder":[81],"continuous":[83],"including":[85],"pitch,":[86],"intensity,":[87],"harmonicity,":[88],"formants,":[89],"cepstral":[90],"peak":[91],"prominence":[92],"octaves.":[94],"We":[95],"extend":[96],"the":[97,111,135,142,145],"text-to-speech":[98],"training":[99,127],"objective":[100],"feature":[102],"reconstruction,":[103],"classification":[104],"speaker":[106],"identification":[107],"tasks":[108],"guide":[110],"to":[113,119,139],"accurate":[115],"result.":[116],"addition":[118],"multitasking,":[120],"also":[122],"employ":[123],"Wasserstein":[125],"GAN":[126],"scheme":[128],"as":[129,131],"well":[130],"new":[132],"losses":[133],"acoustic":[136],"model's":[137],"output":[138],"further":[140],"refine":[141],"quality":[143],"model.":[146]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2022-10-01T00:00:00"}
