{"id":"https://openalex.org/W2571861060","doi":"https://doi.org/10.1109/mmsp.2016.7813372","title":"Two-layer large-scale cover song identification system based on music structure segmentation","display_name":"Two-layer large-scale cover song identification system based on music structure segmentation","publication_year":2016,"publication_date":"2016-09-01","ids":{"openalex":"https://openalex.org/W2571861060","doi":"https://doi.org/10.1109/mmsp.2016.7813372","mag":"2571861060"},"language":"en","primary_location":{"id":"doi:10.1109/mmsp.2016.7813372","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp.2016.7813372","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE 18th International Workshop on Multimedia Signal Processing (MMSP)","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/A5088374967","display_name":"Kang Cai","orcid":"https://orcid.org/0000-0002-8883-0142"},"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":true,"raw_author_name":"Kang Cai","raw_affiliation_strings":["Institute of Computer Science & Technology, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Computer Science & Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100885747","display_name":"Deshun Yang","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":"Deshun Yang","raw_affiliation_strings":["Institute of Computer Science & Technology, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Computer Science & Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","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":["Institute of Computer Science & Technology, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Computer Science & Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5088374967"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.5044,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.66964392,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"20","issue":null,"first_page":"1","last_page":"6"},"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":0.9966999888420105,"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/T10860","display_name":"Speech and Audio Processing","score":0.9767000079154968,"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/computer-science","display_name":"Computer science","score":0.692204475402832},{"id":"https://openalex.org/keywords/cover","display_name":"Cover (algebra)","score":0.6456297636032104},{"id":"https://openalex.org/keywords/chord","display_name":"Chord (peer-to-peer)","score":0.6042372584342957},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5997855067253113},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5602080225944519},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.470054030418396},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.46791771054267883},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.424085408449173},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.4183090925216675},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36786597967147827},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.33655035495758057},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14803314208984375},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.13337719440460205},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.10151177644729614},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.08002549409866333},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07195517420768738}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.692204475402832},{"id":"https://openalex.org/C2780428219","wikidata":"https://www.wikidata.org/wiki/Q16952335","display_name":"Cover (algebra)","level":2,"score":0.6456297636032104},{"id":"https://openalex.org/C194147245","wikidata":"https://www.wikidata.org/wiki/Q1076368","display_name":"Chord (peer-to-peer)","level":2,"score":0.6042372584342957},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5997855067253113},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5602080225944519},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.470054030418396},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.46791771054267883},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.424085408449173},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.4183090925216675},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36786597967147827},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33655035495758057},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14803314208984375},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.13337719440460205},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.10151177644729614},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.08002549409866333},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07195517420768738},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mmsp.2016.7813372","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp.2016.7813372","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE 18th International Workshop on Multimedia Signal Processing (MMSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W41713251","https://openalex.org/W1486009449","https://openalex.org/W1493535305","https://openalex.org/W1554104313","https://openalex.org/W1556219185","https://openalex.org/W1605344066","https://openalex.org/W2018830110","https://openalex.org/W2062533814","https://openalex.org/W2064241329","https://openalex.org/W2107124638","https://openalex.org/W2135392878","https://openalex.org/W2137319814","https://openalex.org/W2138286601","https://openalex.org/W2154473523","https://openalex.org/W2164693078","https://openalex.org/W2167314423","https://openalex.org/W2189280616","https://openalex.org/W2288992572","https://openalex.org/W2394827912","https://openalex.org/W2398493262","https://openalex.org/W6601675542","https://openalex.org/W6628883615","https://openalex.org/W6633146083","https://openalex.org/W6665970074","https://openalex.org/W6687233896","https://openalex.org/W6696285983","https://openalex.org/W6712353197","https://openalex.org/W6712631718"],"related_works":["https://openalex.org/W229552792","https://openalex.org/W2351864507","https://openalex.org/W3215212221","https://openalex.org/W3159818711","https://openalex.org/W2070360846","https://openalex.org/W2042398445","https://openalex.org/W2883093918","https://openalex.org/W4281616442","https://openalex.org/W2407141488","https://openalex.org/W2132792804"],"abstract_inverted_index":{"This":[0],"paper":[1],"focuses":[2],"on":[3,99,110],"cover":[4,41,94,108,146],"song":[5,17,42,95,115,147],"identification":[6,43,96,148],"over":[7],"a":[8,15,22,57,61,83,92,144],"large-scale":[9,39],"dataset.":[10],"Identifying":[11],"all":[12],"covers":[13,26,78],"of":[14,114,130],"query":[16],"from":[18,135],"music":[19,100],"collection":[20],"is":[21,44],"challenging":[23,46],"task":[24],"since":[25],"vary":[27],"in":[28],"multiple":[29],"aspects,":[30],"such":[31,64],"as":[32,65],"tempo,":[33],"key,":[34],"and":[35,47,69],"structure.":[36],"For":[37],"the":[38,75,122,126,152],"dataset,":[40],"more":[45],"few":[48],"works":[49,54],"have":[50],"been":[51],"published.":[52],"Previous":[53],"usually":[55],"use":[56],"single":[58],"representation":[59],"for":[60],"whole":[62],"song,":[63],"2D":[66,131],"Fourier":[67,132],"transform":[68,133],"chord":[70],"profiles,":[71],"which":[72],"cannot":[73],"reflect":[74],"property":[76],"that":[77,121],"are":[79],"largely":[80],"determined":[81],"by":[82],"local":[84],"similarity.":[85],"To":[86],"address":[87],"this":[88],"problem,":[89],"we":[90,141],"propose":[91,143],"novel":[93],"method":[97,106,124,134],"based":[98],"structure":[101],"segmentation.":[102],"The":[103,117],"proposed":[104],"structural":[105,123],"identifies":[107],"songs":[109],"section":[111],"level":[112],"instead":[113],"level.":[116],"experimental":[118],"results":[119],"show":[120],"improves":[125],"mean":[127],"average":[128],"precision":[129],"9.5%":[136],"to":[137,150],"12.1%.":[138],"In":[139],"addition,":[140],"also":[142],"two-layer":[145],"system":[149],"improve":[151],"efficiency.":[153]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}