{"id":"https://openalex.org/W3161928252","doi":"https://doi.org/10.1109/icassp39728.2021.9414128","title":"Bytecover: Cover Song Identification Via Multi-Loss Training","display_name":"Bytecover: Cover Song Identification Via Multi-Loss Training","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3161928252","doi":"https://doi.org/10.1109/icassp39728.2021.9414128","mag":"3161928252"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414128","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414128","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5091528537","display_name":"Xingjian Du","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xingjian Du","raw_affiliation_strings":["Bytedance AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bytedance AI Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031063108","display_name":"Zhesong Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhesong Yu","raw_affiliation_strings":["Bytedance AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bytedance AI Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100934338","display_name":"Bilei Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bilei Zhu","raw_affiliation_strings":["Bytedance AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bytedance AI Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017207620","display_name":"Xiaoou Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoou Chen","raw_affiliation_strings":["Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110851569","display_name":"Zejun Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zejun Ma","raw_affiliation_strings":["Bytedance AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bytedance AI Lab","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.6259,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.9518222,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"551","last_page":"555"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9769999980926514,"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":0.9648000001907349,"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":0.7630816102027893},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.699343204498291},{"id":"https://openalex.org/keywords/cover","display_name":"Cover (algebra)","score":0.559281587600708},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5268318057060242},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.4689732789993286},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46689972281455994},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.4259377419948578},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4237474799156189},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.41965770721435547},{"id":"https://openalex.org/keywords/byte","display_name":"Byte","score":0.41736841201782227},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3783363997936249},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.14256447553634644},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10081765055656433},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08559128642082214}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7630816102027893},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.699343204498291},{"id":"https://openalex.org/C2780428219","wikidata":"https://www.wikidata.org/wiki/Q16952335","display_name":"Cover (algebra)","level":2,"score":0.559281587600708},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5268318057060242},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.4689732789993286},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46689972281455994},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.4259377419948578},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4237474799156189},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41965770721435547},{"id":"https://openalex.org/C43364308","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Byte","level":2,"score":0.41736841201782227},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3783363997936249},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.14256447553634644},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10081765055656433},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08559128642082214},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","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/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414128","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414128","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.5899999737739563}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W130364427","https://openalex.org/W1493535305","https://openalex.org/W2131739315","https://openalex.org/W2137319814","https://openalex.org/W2154473523","https://openalex.org/W2194775991","https://openalex.org/W2408482937","https://openalex.org/W2538860156","https://openalex.org/W2797704180","https://openalex.org/W2884366600","https://openalex.org/W2896276533","https://openalex.org/W2965178495","https://openalex.org/W2967515867","https://openalex.org/W2990171247","https://openalex.org/W2991402284","https://openalex.org/W3009180590","https://openalex.org/W3015271757","https://openalex.org/W3015666964","https://openalex.org/W3137420527","https://openalex.org/W3150415176","https://openalex.org/W4287645101","https://openalex.org/W4393714049","https://openalex.org/W6605313678","https://openalex.org/W6714078465","https://openalex.org/W6729231832","https://openalex.org/W6764992649","https://openalex.org/W6771012916","https://openalex.org/W6783776063","https://openalex.org/W6791444260"],"related_works":["https://openalex.org/W2406877384","https://openalex.org/W2595839522","https://openalex.org/W3109975354","https://openalex.org/W2124576126","https://openalex.org/W1984264321","https://openalex.org/W2357614930","https://openalex.org/W2008642382","https://openalex.org/W1541822869","https://openalex.org/W2037604299","https://openalex.org/W4200069626"],"abstract_inverted_index":{"We":[0],"present":[1],"in":[2,168],"this":[3,135],"paper":[4],"ByteCover,":[5],"which":[6,63],"is":[7,19],"a":[8,116,126,130],"new":[9],"feature":[10],"learning":[11],"method":[12,113,122],"for":[13,41],"cover":[14,144],"song":[15],"identification":[16],"(CSI).":[17],"Byte-Cover":[18],"built":[20],"based":[21],"on":[22,164],"the":[23,36,39,44,49,72,75,88,102,106,111,137,150,158,169,174],"classical":[24],"ResNet":[25],"model,":[26],"and":[27,55,98,119,129,133,140,160,167],"two":[28],"major":[29,65],"improvements":[30],"are":[31,64,85],"designed":[32],"to":[33,59,87,114,123],"further":[34],"enhance":[35],"capability":[37],"of":[38,51,67,74,90,143,155,162],"model":[40,80],"CSI.":[42],"In":[43,105],"first":[45],"improvement,":[46,108],"we":[47,109],"introduce":[48],"integration":[50],"instance":[52],"normalization":[53,57],"(IN)":[54],"batch":[56],"(BN)":[58],"build":[60],"IBN":[61,76],"blocks,":[62,77],"components":[66],"our":[68,78,121],"ResNet-IBN":[69],"model.":[70],"With":[71],"help":[73],"CSI":[79],"can":[81,146],"learn":[82],"features":[83],"that":[84],"invariant":[86],"changes":[89],"musical":[91],"attributes":[92],"such":[93],"as":[94],"key,":[95],"tempo,":[96],"timbre":[97],"genre,":[99],"while":[100],"preserving":[101],"version":[103],"information.":[104],"second":[107],"employ":[110],"BN-Neck":[112],"allow":[115],"multi-loss":[117],"training":[118],"encourage":[120],"jointly":[124],"optimize":[125],"classification":[127],"loss":[128],"triplet":[131],"loss,":[132],"by":[134,178],"means,":[136],"inter-class":[138],"discrimination":[139],"intra-class":[141],"compactness":[142],"songs,":[145],"be":[147],"ensured":[148],"at":[149],"same":[151],"time.":[152],"A":[153],"set":[154],"experiments":[156],"demonstrated":[157],"effectiveness":[159],"efficiency":[161],"ByteCover":[163,172],"multiple":[165],"datasets,":[166],"Da-TACOS":[170],"dataset,":[171],"outperformed":[173],"best":[175],"competitive":[176],"system":[177],"18.0%.":[179]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}