{"id":"https://openalex.org/W3170751106","doi":"https://doi.org/10.1109/icme51207.2021.9428161","title":"Fastsvc: Fast Cross-Domain Singing Voice Conversion With Feature-Wise Linear Modulation","display_name":"Fastsvc: Fast Cross-Domain Singing Voice Conversion With Feature-Wise Linear Modulation","publication_year":2021,"publication_date":"2021-06-09","ids":{"openalex":"https://openalex.org/W3170751106","doi":"https://doi.org/10.1109/icme51207.2021.9428161","mag":"3170751106"},"language":"en","primary_location":{"id":"doi:10.1109/icme51207.2021.9428161","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme51207.2021.9428161","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Multimedia and Expo (ICME)","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/A5102778496","display_name":"Songxiang Liu","orcid":"https://orcid.org/0000-0002-0943-2446"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Songxiang Liu","raw_affiliation_strings":["The Chinese University of Hong Kong,Human-Computer Communications Laboratory","Human-Computer Communications Laboratory, The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Human-Computer Communications Laboratory","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Human-Computer Communications Laboratory, The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013296368","display_name":"Yuewen Cao","orcid":"https://orcid.org/0000-0002-1432-161X"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yuewen Cao","raw_affiliation_strings":["The Chinese University of Hong Kong,Human-Computer Communications Laboratory","Human-Computer Communications Laboratory, The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Human-Computer Communications Laboratory","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Human-Computer Communications Laboratory, The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100685461","display_name":"Na Hu","orcid":"https://orcid.org/0000-0001-6362-0969"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Na Hu","raw_affiliation_strings":["Tencent AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075183307","display_name":"Dan Su","orcid":"https://orcid.org/0000-0001-5746-9545"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Su","raw_affiliation_strings":["Tencent AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019458385","display_name":"Helen Meng","orcid":"https://orcid.org/0000-0002-4427-3532"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Helen Meng","raw_affiliation_strings":["The Chinese University of Hong Kong,Human-Computer Communications Laboratory","Human-Computer Communications Laboratory, The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Human-Computer Communications Laboratory","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Human-Computer Communications Laboratory, The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.7782,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":{"value":0.94289446,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"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":0.9998000264167786,"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":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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/T10860","display_name":"Speech and Audio Processing","score":0.9991999864578247,"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/computer-science","display_name":"Computer science","score":0.7997170686721802},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.6970449090003967},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6048845052719116},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5691738724708557},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.5214371085166931},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.5144239068031311},{"id":"https://openalex.org/keywords/modulation","display_name":"Modulation (music)","score":0.4997286796569824},{"id":"https://openalex.org/keywords/signal-generator","display_name":"Signal generator","score":0.44256898760795593},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42011046409606934},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.2287120223045349},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.11194244027137756},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0820513367652893}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7997170686721802},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.6970449090003967},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6048845052719116},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5691738724708557},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.5214371085166931},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.5144239068031311},{"id":"https://openalex.org/C123079801","wikidata":"https://www.wikidata.org/wiki/Q750240","display_name":"Modulation (music)","level":2,"score":0.4997286796569824},{"id":"https://openalex.org/C207912722","wikidata":"https://www.wikidata.org/wiki/Q1259123","display_name":"Signal generator","level":3,"score":0.44256898760795593},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42011046409606934},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.2287120223045349},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.11194244027137756},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0820513367652893},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C165005293","wikidata":"https://www.wikidata.org/wiki/Q1074500","display_name":"Chip","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme51207.2021.9428161","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme51207.2021.9428161","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Multimedia and Expo (ICME)","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":43,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W2007023536","https://openalex.org/W2067709094","https://openalex.org/W2294038178","https://openalex.org/W2401296648","https://openalex.org/W2471520273","https://openalex.org/W2502312327","https://openalex.org/W2507912506","https://openalex.org/W2519091744","https://openalex.org/W2593414223","https://openalex.org/W2760103357","https://openalex.org/W2940405045","https://openalex.org/W2962866891","https://openalex.org/W2963175743","https://openalex.org/W2970006822","https://openalex.org/W2972812066","https://openalex.org/W2973215447","https://openalex.org/W2989708046","https://openalex.org/W3012498027","https://openalex.org/W3015338123","https://openalex.org/W3016007107","https://openalex.org/W3016243847","https://openalex.org/W3047855478","https://openalex.org/W3095948607","https://openalex.org/W3096084197","https://openalex.org/W3097777922","https://openalex.org/W3123097577","https://openalex.org/W3163568691","https://openalex.org/W4385245566","https://openalex.org/W6623517193","https://openalex.org/W6629717138","https://openalex.org/W6631190155","https://openalex.org/W6724804524","https://openalex.org/W6739901393","https://openalex.org/W6740674931","https://openalex.org/W6767111847","https://openalex.org/W6770046961","https://openalex.org/W6781547035","https://openalex.org/W6782760101","https://openalex.org/W6784691655","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W3128433826","https://openalex.org/W2168529281","https://openalex.org/W978543704","https://openalex.org/W2378673986","https://openalex.org/W2371180536","https://openalex.org/W2387706796","https://openalex.org/W2380432131","https://openalex.org/W2391206061","https://openalex.org/W2385502811","https://openalex.org/W2978914987"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"FastSVC,":[3],"a":[4,71,89],"light-weight":[5],"cross-domain":[6],"singing":[7,38,118],"voice":[8],"conversion":[9,16,97,105,119],"(SVC)":[10],"system,":[11,86,93],"which":[12],"can":[13,66,94],"achieve":[14,95],"high":[15],"performance,":[17],"with":[18,88],"inference":[19,122],"speed":[20,123],"4x":[21],"faster":[22,132],"than":[23,133],"real-time":[24],"on":[25,137],"CPUs.":[26],"FastSVC":[27,85,113,126],"uses":[28],"Conformer-based":[29],"phoneme":[30],"recognizer":[31],"to":[32,48],"extract":[33],"singer-agnostic":[34],"linguistic":[35,53],"features":[36],"from":[37,52,57],"signals.":[39],"A":[40],"feature-wise":[41],"linear":[42],"modulation":[43],"based":[44],"generator":[45,65],"is":[46,128],"used":[47],"synthesize":[49],"waveform":[50,64],"directly":[51],"features,":[54],"leveraging":[55],"information":[56],"sine-excitation":[58],"signals":[59],"and":[60,75,102,130,139],"loudness":[61],"features.":[62],"The":[63,121],"be":[67],"trained":[68],"conveniently":[69],"using":[70],"multi-resolution":[72],"spectral":[73],"loss":[74],"an":[76],"adversarial":[77],"loss.":[78],"Experimental":[79],"results":[80],"show":[81],"that":[82],"the":[83,111,125,134],"proposed":[84,112],"compared":[87],"computationally":[90],"heavy":[91],"baseline":[92,135],"comparable":[96],"performance":[98,106],"in":[99,107],"some":[100],"scenarios":[101],"significantly":[103],"better":[104],"other":[108],"scenarios.":[109],"Moreover,":[110],"system":[114,127,136],"achieves":[115],"desirable":[116],"cross-lingual":[117],"performance.":[120],"of":[124],"3x":[129],"70x":[131],"GPUs":[138],"CPUs,":[140],"respectively.":[141]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}