{"id":"https://openalex.org/W4372266723","doi":"https://doi.org/10.1109/icassp49357.2023.10095389","title":"Bytecover3: Accurate Cover Song Identification On Short Queries","display_name":"Bytecover3: Accurate Cover Song Identification On Short Queries","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372266723","doi":"https://doi.org/10.1109/icassp49357.2023.10095389"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095389","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095389","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5091528537","display_name":"Xingjian Du","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xingjian Du","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008885538","display_name":"Zijie Wang","orcid":"https://orcid.org/0000-0001-7974-7075"},"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":"Zijie Wang","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100713965","display_name":"Liang Xia","orcid":"https://orcid.org/0000-0002-5780-4435"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xia Liang","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035381555","display_name":"Huidong Liang","orcid":"https://orcid.org/0000-0001-5960-2741"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Huidong Liang","raw_affiliation_strings":["University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101108160","display_name":"Zejun Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zejun Ma","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2933,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.80159713,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"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/T11309","display_name":"Music and Audio Processing","score":1.0,"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":1.0,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9908000230789185,"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"}},{"id":"https://openalex.org/T13996","display_name":"Diverse Musicological Studies","score":0.9821000099182129,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8078581094741821},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6283601522445679},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6212391257286072},{"id":"https://openalex.org/keywords/upgrade","display_name":"Upgrade","score":0.587755024433136},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5307419896125793},{"id":"https://openalex.org/keywords/cover","display_name":"Cover (algebra)","score":0.5285110473632812},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4377695322036743},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4216611385345459},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.41513872146606445},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4121033549308777},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3891009986400604},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3594517707824707},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3461334705352783},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.07568284869194031},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07182666659355164}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8078581094741821},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6283601522445679},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6212391257286072},{"id":"https://openalex.org/C2780615140","wikidata":"https://www.wikidata.org/wiki/Q920419","display_name":"Upgrade","level":2,"score":0.587755024433136},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5307419896125793},{"id":"https://openalex.org/C2780428219","wikidata":"https://www.wikidata.org/wiki/Q16952335","display_name":"Cover (algebra)","level":2,"score":0.5285110473632812},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4377695322036743},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4216611385345459},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.41513872146606445},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4121033549308777},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3891009986400604},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3594517707824707},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3461334705352783},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.07568284869194031},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07182666659355164},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095389","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095389","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5899999737739563,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W166844666","https://openalex.org/W2025763800","https://openalex.org/W2130865646","https://openalex.org/W2150555104","https://openalex.org/W2154473523","https://openalex.org/W2194775991","https://openalex.org/W2571861060","https://openalex.org/W2896276533","https://openalex.org/W2963469388","https://openalex.org/W2965178495","https://openalex.org/W2991402284","https://openalex.org/W3015271757","https://openalex.org/W3015666964","https://openalex.org/W3034303554","https://openalex.org/W3161928252","https://openalex.org/W3163858829","https://openalex.org/W4224920338","https://openalex.org/W4287645101","https://openalex.org/W4297841704","https://openalex.org/W6764992649","https://openalex.org/W6783776063"],"related_works":["https://openalex.org/W2368672678","https://openalex.org/W2965111880","https://openalex.org/W2370626080","https://openalex.org/W2368576029","https://openalex.org/W2377210208","https://openalex.org/W116478885","https://openalex.org/W2391279445","https://openalex.org/W2390420166","https://openalex.org/W2354998446","https://openalex.org/W2361591611"],"abstract_inverted_index":{"Deep":[0],"learning":[1],"based":[2],"methods":[3,133],"have":[4,20],"become":[5],"a":[6,92,99,111],"paradigm":[7],"for":[8,59],"cover":[9],"song":[10],"identification":[11,82],"(CSI)":[12],"in":[13,50,110],"recent":[14],"years,":[15],"where":[16,127],"the":[17,26,33,51,68,81,105,131],"ByteCover":[18,70],"systems":[19,71],"achieved":[21],"state-of-the-art":[22],"results":[23],"on":[24,120],"all":[25,130],"mainstream":[27],"datasets":[28,122],"of":[29,35,84],"CSI.":[30],"However,":[31],"with":[32,91,123],"burgeon":[34],"short":[36,43,85],"videos,":[37],"many":[38],"real-world":[39],"applications":[40],"require":[41],"matching":[42],"music":[44,48,86],"excerpts":[45],"to":[46,72,78,107],"full-length":[47],"tracks":[49],"database,":[52],"which":[53],"is":[54,89],"still":[55],"under-explored":[56],"and":[57,98,114],"waiting":[58],"an":[60],"industrial-level":[61],"solution.":[62],"In":[63],"this":[64],"paper,":[65],"we":[66],"upgrade":[67],"previous":[69,136],"ByteCover3":[73,88,119,128],"that":[74],"utilizes":[75],"local":[76,93],"features":[77],"further":[79],"improve":[80],"performance":[83],"queries.":[87],"designed":[90],"alignment":[94],"loss":[95],"(LAL)":[96],"module":[97],"two-stage":[100],"feature":[101],"retrieval":[102],"pipeline,":[103],"allowing":[104],"system":[106],"perform":[108],"CSI":[109],"more":[112],"precise":[113],"efficient":[115],"way.":[116],"We":[117],"evaluated":[118],"multiple":[121],"different":[124],"benchmark":[125],"settings,":[126],"beat":[129],"compared":[132],"including":[134],"its":[135],"versions.":[137]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}