{"id":"https://openalex.org/W4408353929","doi":"https://doi.org/10.1109/icassp49660.2025.10887782","title":"Singing Voice Conversion with Accompaniment Using Self-Supervised Representation-Based Melody Features","display_name":"Singing Voice Conversion with Accompaniment Using Self-Supervised Representation-Based Melody Features","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353929","doi":"https://doi.org/10.1109/icassp49660.2025.10887782"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887782","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887782","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5108049716","display_name":"Wei Chen","orcid":"https://orcid.org/0000-0002-9066-1448"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wei Chen","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093470868","display_name":"Binzhu Sha","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Binzhu Sha","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100378741","display_name":"H. J. Yang","orcid":"https://orcid.org/0009-0004-8274-9863"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Yang","raw_affiliation_strings":["Huawei Technologies Co., Ltd,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd,Shenzhen,China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100446586","display_name":"Zhuo Wang","orcid":"https://orcid.org/0000-0002-5589-0288"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuo Wang","raw_affiliation_strings":["Huawei Technologies Co., Ltd,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd,Shenzhen,China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107911728","display_name":"Fan Fan","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Fan","raw_affiliation_strings":["Huawei Technologies Co., Ltd,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd,Shenzhen,China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111019783","display_name":"Zhiyong Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyong Wu","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5108049716"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":1.561,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.78386442,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9886999726295471,"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/T10860","display_name":"Speech and Audio Processing","score":0.9886999726295471,"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":0.9616000056266785,"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":0.9606999754905701,"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":0.9260467290878296},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7415985465049744},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7283194065093994},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5473822951316833},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36862075328826904},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.16062691807746887}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.9260467290878296},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7415985465049744},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7283194065093994},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5473822951316833},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36862075328826904},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.16062691807746887},{"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10887782","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887782","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1590808459","https://openalex.org/W2007023536","https://openalex.org/W2060277733","https://openalex.org/W2118774185","https://openalex.org/W2294038178","https://openalex.org/W2401296648","https://openalex.org/W2518172956","https://openalex.org/W2962866891","https://openalex.org/W2964243274","https://openalex.org/W3016243847","https://openalex.org/W3097152652","https://openalex.org/W3163568691","https://openalex.org/W3170751106","https://openalex.org/W3197478142","https://openalex.org/W3199364993","https://openalex.org/W3205154814","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4224927653","https://openalex.org/W4225096077","https://openalex.org/W4225322394","https://openalex.org/W4226320669","https://openalex.org/W4226403810","https://openalex.org/W4285345683","https://openalex.org/W4296068763","https://openalex.org/W4372260250","https://openalex.org/W4372338328","https://openalex.org/W4386158910","https://openalex.org/W4391021724","https://openalex.org/W4391021798","https://openalex.org/W4405709643","https://openalex.org/W6729110096","https://openalex.org/W6766320909","https://openalex.org/W6778823374","https://openalex.org/W6783867762"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","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"],"abstract_inverted_index":{"Melody":[0],"preservation":[1],"is":[2,14],"crucial":[3],"in":[4,10,61,86,116,165,176],"singing":[5],"voice":[6],"conversion":[7,87],"(SVC).":[8],"However,":[9],"many":[11],"scenarios,":[12],"audio":[13,24,186],"often":[15,77],"accompanied":[16],"with":[17,28],"background":[18],"music":[19],"(BGM),":[20],"which":[21],"can":[22],"cause":[23],"distortion":[25],"and":[26,33,89,137,170,174,179,184],"interfere":[27],"the":[29,62,91,117,126,140,146],"extraction":[30,136],"of":[31,64,119,128,148,167],"melody":[32,54,109,113,135,149,168],"other":[34],"key":[35],"features,":[36],"significantly":[37,160],"degrading":[38],"SVC":[39,103,158],"performance.":[40],"Previous":[41],"methods":[42,164],"have":[43],"attempted":[44],"to":[45,82,111],"address":[46,96],"this":[47,76],"by":[48],"using":[49],"more":[50],"robust":[51],"neural":[52],"network-based":[53],"extractors,":[55],"but":[56,75],"their":[57],"performance":[58],"drops":[59],"sharply":[60],"presence":[63,118],"complex":[65],"accompaniment.":[66],"Other":[67],"approaches":[68],"involve":[69],"performing":[70],"source":[71],"separation":[72],"before":[73],"conversion,":[74],"introduces":[78],"noticeable":[79],"artifacts,":[80],"leading":[81],"a":[83,101],"significant":[84],"drop":[85],"quality":[88],"increasing":[90],"user\u2019s":[92],"operational":[93],"costs.":[94],"To":[95],"these":[97],"issues,":[98],"we":[99,124],"introduce":[100],"novel":[102],"method":[104],"that":[105,155],"uses":[106],"self-supervised":[107,130],"representation-based":[108],"features":[110],"improve":[112],"modeling":[114],"accuracy":[115,169],"BGM.":[120],"In":[121],"our":[122,156],"experiments,":[123],"compare":[125],"effectiveness":[127],"different":[129],"learning":[131],"(SSL)":[132],"models":[133],"for":[134,139],"explore":[138],"first":[141],"time":[142],"how":[143],"SSL":[144],"benefits":[145],"task":[147],"extraction.":[150],"The":[151],"experimental":[152],"results":[153],"demonstrate":[154],"proposed":[157],"model":[159],"outperforms":[161],"existing":[162],"baseline":[163],"terms":[166],"shows":[171],"higher":[172],"similarity":[173],"naturalness":[175],"both":[177],"subjective":[178],"objective":[180],"evaluations":[181],"across":[182],"noisy":[183],"clean":[185],"environments.":[187]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}