{"id":"https://openalex.org/W4384643806","doi":"https://doi.org/10.1145/3539618.3591664","title":"DisCover: Disentangled Music Representation Learning for Cover Song Identification","display_name":"DisCover: Disentangled Music Representation Learning for Cover Song Identification","publication_year":2023,"publication_date":"2023-07-18","ids":{"openalex":"https://openalex.org/W4384643806","doi":"https://doi.org/10.1145/3539618.3591664"},"language":"en","primary_location":{"id":"doi:10.1145/3539618.3591664","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3539618.3591664","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","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/A5016873117","display_name":"Jiahao Xun","orcid":"https://orcid.org/0009-0000-6141-4125"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiahao Xun","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0000-6141-4125","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100757087","display_name":"Shengyu Zhang","orcid":"https://orcid.org/0000-0002-0030-8289"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengyu Zhang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-0030-8289","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103070122","display_name":"Yanting Yang","orcid":"https://orcid.org/0009-0005-1969-0747"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanting Yang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0005-1969-0747","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048669373","display_name":"Jieming Zhu","orcid":"https://orcid.org/0000-0002-5666-8320"},"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":"Jieming Zhu","raw_affiliation_strings":["Huawei Noah's Ark Lab, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-5666-8320","affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044738402","display_name":"Liqun Deng","orcid":"https://orcid.org/0009-0006-7242-0794"},"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":"Liqun Deng","raw_affiliation_strings":["Huawei Noah's Ark Lab, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0006-7242-0794","affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079260216","display_name":"Zhou Zhao","orcid":"https://orcid.org/0000-0001-6121-0384"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou Zhao","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-6121-0384","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021124418","display_name":"Zhenhua Dong","orcid":"https://orcid.org/0000-0002-2231-4663"},"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":"Zhenhua Dong","raw_affiliation_strings":["Huawei Noah's Ark Lab, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-2231-4663","affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082434874","display_name":"Ruiqi Li","orcid":"https://orcid.org/0009-0005-3798-6568"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruiqi Li","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0005-3798-6568","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067136900","display_name":"Lichao Zhang","orcid":"https://orcid.org/0009-0009-0389-4090"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lichao Zhang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0009-0389-4090","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004882141","display_name":"Fei Wu","orcid":"https://orcid.org/0000-0003-2139-8807"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Wu","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-2139-8807","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"453","last_page":"463"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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/T13996","display_name":"Diverse Musicological Studies","score":0.9660000205039978,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9598000049591064,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7478474378585815},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.6361405849456787},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.6355699300765991},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5351195335388184},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.5300291180610657},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.49202486872673035},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.48836371302604675},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.46424898505210876},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44863903522491455},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4415279030799866},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4302450716495514},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.42434653639793396},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3839758038520813},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.25455132126808167},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11178469657897949}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7478474378585815},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.6361405849456787},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.6355699300765991},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5351195335388184},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5300291180610657},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.49202486872673035},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.48836371302604675},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.46424898505210876},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44863903522491455},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4415279030799866},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4302450716495514},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.42434653639793396},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3839758038520813},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.25455132126808167},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11178469657897949},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","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/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3539618.3591664","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3539618.3591664","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3872996613","display_name":null,"funder_award_id":"61836002","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G955845854","display_name":null,"funder_award_id":"62222211,62072397","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W2131739315","https://openalex.org/W2137319814","https://openalex.org/W2138286601","https://openalex.org/W2154473523","https://openalex.org/W2295107390","https://openalex.org/W2747329762","https://openalex.org/W2896276533","https://openalex.org/W2906259846","https://openalex.org/W2914327968","https://openalex.org/W2962858109","https://openalex.org/W2963435138","https://openalex.org/W2963451564","https://openalex.org/W2965178495","https://openalex.org/W2972745288","https://openalex.org/W3015271757","https://openalex.org/W3015625764","https://openalex.org/W3015666964","https://openalex.org/W3033630125","https://openalex.org/W3038585207","https://openalex.org/W3088203142","https://openalex.org/W3092850823","https://openalex.org/W3116172555","https://openalex.org/W3152876231","https://openalex.org/W3158762648","https://openalex.org/W3160719641","https://openalex.org/W3161928252","https://openalex.org/W3162391496","https://openalex.org/W3164548985","https://openalex.org/W3168738558","https://openalex.org/W3176013316","https://openalex.org/W3205091761","https://openalex.org/W3205234797","https://openalex.org/W3206191467","https://openalex.org/W3208604322","https://openalex.org/W3213539234","https://openalex.org/W3214584541","https://openalex.org/W4220931296","https://openalex.org/W4224308683","https://openalex.org/W4224920338","https://openalex.org/W4225280403","https://openalex.org/W4281777295","https://openalex.org/W4285345683","https://openalex.org/W4304099317","https://openalex.org/W4306175879","https://openalex.org/W4312878209","https://openalex.org/W6602452458"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W1590307681","https://openalex.org/W4312814274","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2502115930","https://openalex.org/W2358353312","https://openalex.org/W2242773987"],"abstract_inverted_index":{"In":[0,54],"the":[1,43,59,73,86,94,100,106,115,152,156,175,197,202],"field":[2],"of":[3,22,46,61,126,199,205],"music":[4,78,117],"information":[5,154],"retrieval":[6],"(MIR),":[7],"cover":[8,20],"song":[9,25],"identification":[10],"(CSI)":[11],"is":[12],"a":[13,23,27,90],"challenging":[14],"task":[15,88],"that":[16,162],"aims":[17],"to":[18,42,75],"identify":[19,99],"versions":[21],"query":[24,82],"from":[26,34],"massive":[28],"collection.":[29],"Existing":[30],"works":[31],"still":[32],"suffer":[33],"high":[35],"intra-song":[36,179],"variances":[37],"and":[38,48,64,98,102,135,145,159,181,193,201,203],"inter-song":[39],"correlations,":[40],"due":[41],"entangled":[44],"nature":[45],"version-specific":[47,63],"version-invariant":[49,65],"factors":[50,161,172],"in":[51,89],"their":[52],"modeling.":[53],"this":[55],"work,":[56],"we":[57,113],"set":[58],"goal":[60],"disentangling":[62],"factors,":[66],"which":[67,142],"could":[68],"make":[69],"it":[70],"easier":[71],"for":[72,80,122,185,207],"model":[74],"learn":[76],"invariant":[77,107],"representations":[79,158],"unseen":[81],"songs.":[83],"We":[84],"analyze":[85],"CSI":[87],"disentanglement":[91,206],"view":[92],"with":[93,165,190],"causal":[95],"graph":[96],"technique,":[97],"intra-version":[101,144],"inter-version":[103,146],"effects":[104],"biasing":[105],"learning.":[108],"To":[109],"block":[110,143],"these":[111],"effects,":[112,148],"propose":[114],"disentangled":[116],"representation":[118,176],"learning":[119],"framework":[120],"(DisCover)":[121],"CSI.":[123,208],"DisCover":[124,200],"consists":[125],"two":[127],"critical":[128],"components:":[129],"(1)":[130],"Knowledge-guided":[131],"Disentanglement":[132,139],"Module":[133,140],"(KDM)":[134],"(2)":[136],"Gradient-based":[137],"Adversarial":[138],"(GADM),":[141],"biased":[147],"respectively.":[149],"KDM":[150],"minimizes":[151],"mutual":[153],"between":[155,178],"learned":[157],"version-variant":[160,171],"are":[163],"identified":[164],"prior":[166],"domain":[167],"knowledge.":[168],"GADM":[169],"identifies":[170],"by":[173],"simulating":[174],"transitions":[177],"versions,":[180],"exploits":[182],"adversarial":[183],"distillation":[184],"effect":[186],"blocking.":[187],"Extensive":[188],"comparisons":[189],"best-performing":[191],"methods":[192],"in-depth":[194],"analysis":[195],"demonstrate":[196],"effectiveness":[198],"necessity":[204]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}