{"id":"https://openalex.org/W4401597614","doi":"https://doi.org/10.1109/icasspw62465.2024.10626580","title":"Low-Resource Cross-Domain Singing Voice Synthesis via Reduced Self-Supervised Speech Representations","display_name":"Low-Resource Cross-Domain Singing Voice Synthesis via Reduced Self-Supervised Speech Representations","publication_year":2024,"publication_date":"2024-04-14","ids":{"openalex":"https://openalex.org/W4401597614","doi":"https://doi.org/10.1109/icasspw62465.2024.10626580"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw62465.2024.10626580","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icasspw62465.2024.10626580","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","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/A5067728489","display_name":"Panos Kakoulidis","orcid":"https://orcid.org/0000-0003-2980-2528"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Panos Kakoulidis","raw_affiliation_strings":["Samsung Electronics,Innoetics,Greece"],"affiliations":[{"raw_affiliation_string":"Samsung Electronics,Innoetics,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":["Samsung Electronics,Innoetics,Greece"],"affiliations":[{"raw_affiliation_string":"Samsung Electronics,Innoetics,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":["Samsung Electronics,Innoetics,Greece"],"affiliations":[{"raw_affiliation_string":"Samsung Electronics,Innoetics,Greece","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061303593","display_name":"Myrsini Christidou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Myrsini Christidou","raw_affiliation_strings":["Samsung Electronics,Innoetics,Greece"],"affiliations":[{"raw_affiliation_string":"Samsung Electronics,Innoetics,Greece","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015840293","display_name":"Alexandra Vioni","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexandra Vioni","raw_affiliation_strings":["Samsung Electronics,Innoetics,Greece"],"affiliations":[{"raw_affiliation_string":"Samsung Electronics,Innoetics,Greece","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037667852","display_name":"Georgia Maniati","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Georgia Maniati","raw_affiliation_strings":["Samsung Electronics,Innoetics,Greece"],"affiliations":[{"raw_affiliation_string":"Samsung Electronics,Innoetics,Greece","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113307596","display_name":"Junkwang Oh","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":"Junkwang Oh","raw_affiliation_strings":["Samsung Electronics,Mobile Communications Business,Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Electronics,Mobile Communications Business,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":["Samsung Electronics,Mobile Communications Business,Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Electronics,Mobile Communications Business,Republic of Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101882326","display_name":"In-Chul Hwang","orcid":"https://orcid.org/0000-0002-0045-9984"},"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":"Inchul Hwang","raw_affiliation_strings":["Samsung Electronics,Mobile Communications Business,Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Electronics,Mobile Communications Business,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":["Samsung Electronics,Innoetics,Greece"],"affiliations":[{"raw_affiliation_string":"Samsung Electronics,Innoetics,Greece","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108894078","display_name":"Aimilios Chalamandaris","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aimilios Chalamandaris","raw_affiliation_strings":["Samsung Electronics,Innoetics,Greece"],"affiliations":[{"raw_affiliation_string":"Samsung Electronics,Innoetics,Greece","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5067728489"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3862,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.65935401,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"33","issue":null,"first_page":"605","last_page":"609"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9957000017166138,"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":0.9957000017166138,"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":0.9846000075340271,"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/T11309","display_name":"Music and Audio Processing","score":0.9711999893188477,"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/speech-recognition","display_name":"Speech recognition","score":0.6866926550865173},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.678527295589447},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.5898875594139099},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5386388897895813},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4866858124732971},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3971746265888214},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32795095443725586},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.11184009909629822},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10444548726081848}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6866926550865173},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.678527295589447},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.5898875594139099},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5386388897895813},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4866858124732971},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3971746265888214},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32795095443725586},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.11184009909629822},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10444548726081848},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icasspw62465.2024.10626580","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icasspw62465.2024.10626580","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2502312327","https://openalex.org/W2622563070","https://openalex.org/W2785678896","https://openalex.org/W2899663614","https://openalex.org/W2936774411","https://openalex.org/W2963091184","https://openalex.org/W2972359262","https://openalex.org/W3097777922","https://openalex.org/W3158762648","https://openalex.org/W3170751106","https://openalex.org/W3209984917","https://openalex.org/W4288257146","https://openalex.org/W4297841449","https://openalex.org/W4323651091","https://openalex.org/W4366460484","https://openalex.org/W4372266915","https://openalex.org/W4372347654","https://openalex.org/W4375869015","https://openalex.org/W4385571362","https://openalex.org/W4385823074","https://openalex.org/W4385823416","https://openalex.org/W4385895691","https://openalex.org/W4388979610","https://openalex.org/W4391021724","https://openalex.org/W4391305764","https://openalex.org/W6631190155","https://openalex.org/W6724804524","https://openalex.org/W6738560588","https://openalex.org/W6755977528","https://openalex.org/W6778823374","https://openalex.org/W6780218876","https://openalex.org/W6781550413","https://openalex.org/W6790220310","https://openalex.org/W6796464841","https://openalex.org/W6838910450","https://openalex.org/W6850334629","https://openalex.org/W6851724922","https://openalex.org/W6853844661"],"related_works":["https://openalex.org/W2390529913","https://openalex.org/W2142368101","https://openalex.org/W2372249404","https://openalex.org/W2367547137","https://openalex.org/W2354994102","https://openalex.org/W2387733758","https://openalex.org/W2376664795","https://openalex.org/W2366077683","https://openalex.org/W1501596003","https://openalex.org/W127416991"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,131],"propose":[4],"a":[5,21,28,66,90,133,145],"singing":[6,36,105],"voice":[7,106,129],"synthesis":[8,107],"model,":[9],"Karaoker-SSL,":[10],"that":[11,31,136],"is":[12,27,42,49,75,87,137],"trained":[13,44],"only":[14,65],"on":[15,45,110,139],"text":[16,121],"and":[17,112,143],"speech":[18,46,53],"data":[19,37],"as":[20],"typical":[22],"multi-speaker":[23],"acoustic":[24,99],"model.":[25],"It":[26],"low-resource":[29],"pipeline":[30],"does":[32],"not":[33],"utilize":[34],"any":[35],"end-to-end,":[38],"since":[39],"its":[40],"vocoder":[41],"also":[43,117],"data.":[47],"Karaoker-SSL":[48,103],"conditioned":[50,138],"by":[51,63,84],"self-supervised":[52],"representations":[54,62],"in":[55],"an":[56],"unsupervised":[57],"manner.":[58],"We":[59],"preprocess":[60],"these":[61],"selecting":[64],"subset":[67],"of":[68],"their":[69],"task-correlated":[70],"dimensions.":[71],"The":[72],"conditioning":[73],"module":[74],"indirectly":[76],"guided":[77],"to":[78],"capture":[79],"style":[80],"information":[81],"during":[82],"training":[83,148],"multi-tasking.":[85],"This":[86],"achieved":[88],"with":[89],"Conformer-based":[91],"module,":[92],"which":[93],"predicts":[94],"the":[95,98,128,140],"pitch":[96],"from":[97],"model\u2019s":[100],"output.":[101],"Thus,":[102],"allows":[104],"without":[108],"reliance":[109],"hand-crafted":[111],"domain-specific":[113],"features.":[114],"There":[115],"are":[116],"no":[118],"requirements":[119],"for":[120],"alignments":[122],"or":[123],"lyrics":[124],"timestamps.":[125],"To":[126],"refine":[127],"quality,":[130],"employ":[132],"U-Net":[134],"discriminator":[135],"target":[141],"speaker":[142],"follows":[144],"Diffusion":[146],"GAN":[147],"scheme.":[149]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}
