{"id":"https://openalex.org/W4392931776","doi":"https://doi.org/10.1109/icassp48485.2024.10446284","title":"ESVC: Combining Adaptive Style Fusion and Multi-Level Feature Disentanglement for Expressive Singing Voice Conversion","display_name":"ESVC: Combining Adaptive Style Fusion and Multi-Level Feature Disentanglement for Expressive Singing Voice Conversion","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392931776","doi":"https://doi.org/10.1109/icassp48485.2024.10446284"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446284","doi":"https://doi.org/10.1109/icassp48485.2024.10446284","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10446284","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"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":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5017990705","display_name":"Zeyu Yang","orcid":"https://orcid.org/0000-0003-0253-9053","observed_orcids":["https://orcid.org/0000-0003-0253-9053","https://orcid.org/0000-0002-1596-6890"]},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zeyu Yang","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059638789","display_name":"Minchuan Chen","orcid":"https://orcid.org/0009-0001-1512-6672","observed_orcids":["https://orcid.org/0009-0001-1512-6672"]},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minchuan Chen","raw_affiliation_strings":["Ping An Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology, China","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100385632","display_name":"Yanping Li","orcid":"https://orcid.org/0000-0002-0074-7695","observed_orcids":["https://orcid.org/0000-0002-0074-7695"]},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanping Li","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101857152","display_name":"Wei Hu","orcid":"https://orcid.org/0000-0002-3744-8357","observed_orcids":["https://orcid.org/0000-0002-3744-8357"]},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Hu","raw_affiliation_strings":["Ping An Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology, China","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100702017","display_name":"Shaojun Wang","orcid":"https://orcid.org/0009-0001-8955-8566","observed_orcids":["https://orcid.org/0009-0001-8955-8566"]},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaojun Wang","raw_affiliation_strings":["Ping An Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology, China","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016038454","display_name":"Jing Zhong Xiao","orcid":"https://orcid.org/0000-0001-9615-4749","observed_orcids":["https://orcid.org/0000-0001-9615-4749","https://orcid.org/0009-0003-7045-5537"]},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Xiao","raw_affiliation_strings":["Ping An Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology, China","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"last","author":{"id":null,"display_name":"Zijian Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zijian Li","raw_affiliation_strings":["Georgia Institute of Technology, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3157,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.51827575,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"12161","last_page":"12165"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.913100004196167,"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":0.913100004196167,"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":0.05079999938607216,"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":0.012199999764561653,"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-voice-conversion","display_name":"singing voice conversion","score":0.9639999866485596},{"id":"https://openalex.org/keywords/emotional-style","display_name":"emotional style","score":0.578000009059906},{"id":"https://openalex.org/keywords/style-fusion","display_name":"style fusion","score":0.7070000171661377},{"id":"https://openalex.org/keywords/feature-disentanglement","display_name":"feature disentanglement","score":0.9359999895095825},{"id":"https://openalex.org/keywords/adaptive-instance-normalization","display_name":"adaptive instance normalization","score":0.9710000157356262},{"id":"https://openalex.org/keywords/mutual-information","display_name":"mutual information","score":0.8420000076293945},{"id":"https://openalex.org/keywords/fundamental-frequency","display_name":"fundamental frequency","score":0.9259999990463257},{"id":"https://openalex.org/keywords/information-leakage","display_name":"information leakage","score":0.460999995470047}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.6939625144004822},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.683009147644043},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5620689988136292},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.5583041906356812},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5387678146362305},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.520763635635376},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.5049529671669006},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.5038232207298279},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.45736369490623474},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.4495089650154114},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3661193251609802},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.19701698422431946},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08872547745704651},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"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/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446284","doi":"https://doi.org/10.1109/icassp48485.2024.10446284","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10446284","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"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":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320323268","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34"},{"id":"https://openalex.org/F4320324852","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W2066598518","https://openalex.org/W2096733369","https://openalex.org/W2294038178","https://openalex.org/W2603777577","https://openalex.org/W3016007107","https://openalex.org/W3035060230","https://openalex.org/W3048203730","https://openalex.org/W3096939667","https://openalex.org/W3110041771","https://openalex.org/W3163568691","https://openalex.org/W3169320628","https://openalex.org/W3169905056","https://openalex.org/W3197659778","https://openalex.org/W3205154814","https://openalex.org/W3207300132","https://openalex.org/W3209984917","https://openalex.org/W3210530853","https://openalex.org/W4205742757","https://openalex.org/W4221153051","https://openalex.org/W4224927653","https://openalex.org/W4226320669","https://openalex.org/W4283659485","https://openalex.org/W4285345683","https://openalex.org/W4286747238","https://openalex.org/W4296068763","https://openalex.org/W4372260053","https://openalex.org/W4372338328","https://openalex.org/W4384028538","https://openalex.org/W4391021367","https://openalex.org/W4391021724","https://openalex.org/W4406794071"],"related_works":["https://openalex.org/W4286747238","https://openalex.org/W4226474318","https://openalex.org/W3205065526","https://openalex.org/W4404915703","https://openalex.org/W4400621997","https://openalex.org/W4415433552","https://openalex.org/W4404688059","https://openalex.org/W7155075458","https://openalex.org/W6910970622","https://openalex.org/W4392909515"],"abstract_inverted_index":{"Nowadays,":[0],"singing":[1,124],"voice":[2],"conversion":[3],"(SVC)":[4],"has":[5],"made":[6],"great":[7],"strides":[8],"in":[9,80,190],"both":[10],"naturalness":[11],"and":[12,35,62,73,85,104,141,153,173,177],"similarity":[13],"for":[14,89,150],"common":[15],"SVC":[16,39,53,166,188],"with":[17],"a":[18],"neutral":[19],"expression.":[20],"However,":[21],"besides":[22],"singer":[23,60,86,171],"identity,":[24],"emotional":[25,63,83,154,174],"expression":[26],"is":[27,129,148,163],"also":[28],"essential":[29],"to":[30,77,99,119,131,168],"convey":[31],"the":[32,68,101,109,133,157,164,186],"singer\u2019s":[33],"emotions":[34],"attitudes,":[36],"but":[37],"current":[38],"systems":[40],"can":[41,58],"not":[42],"effectively":[43],"support":[44],"it.":[45],"In":[46],"this":[47],"paper,":[48],"we":[49,93],"propose":[50],"an":[51],"expressive":[52,142],"framework":[54],"called":[55],"ESVC,":[56],"which":[57],"convert":[59,170],"identity":[61,152,172],"style":[64,71,84,90,105,193],"simultaneously.":[65],"ESVC":[66,162],"combines":[67],"ideas":[69],"of":[70,82,111,123,159,192],"fusion":[72],"feature":[74,103],"disentanglement,":[75],"seeking":[76],"maximize":[78],"fidelity":[79],"terms":[81,191],"identity.":[87],"Firstly,":[88],"information":[91,112,127],"penetration,":[92],"employ":[94],"adaptive":[95],"instance":[96],"normalization":[97],"(AdaIN)":[98],"fuse":[100],"content":[102],"feature.":[106],"Secondly,":[107],"given":[108],"possibility":[110],"leakage,":[113],"two":[114],"disentanglement-oriented":[115],"methods":[116],"are":[117],"introduced":[118],"decouple":[120],"different":[121],"kinds":[122],"features.":[125],"Mutual":[126],"(MI)":[128],"used":[130],"reduce":[132],"correlation":[134],"between":[135],"linguistic":[136],"content,":[137],"fundamental":[138],"frequency":[139],"(F0)":[140],"feature,":[143],"while":[144],"adversarial":[145],"triplet":[146],"loss":[147],"exerted":[149],"decoupling":[151],"elements.":[155],"To":[156],"best":[158],"our":[160,182],"knowledge,":[161],"first":[165],"system":[167,183],"jointly":[169],"style.":[175],"Objective":[176],"subjective":[178],"experiments":[179],"demonstrate":[180],"that":[181],"significantly":[184],"outperforms":[185],"state-of-the-art":[187],"model":[189],"expressiveness.":[194]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2024-03-19T00:00:00"}