{"id":"https://openalex.org/W3015666964","doi":"https://doi.org/10.1109/icassp40776.2020.9053839","title":"Learning a Representation for Cover Song Identification Using Convolutional Neural Network","display_name":"Learning a Representation for Cover Song Identification Using Convolutional Neural Network","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015666964","doi":"https://doi.org/10.1109/icassp40776.2020.9053839","mag":"3015666964"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053839","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053839","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5031063108","display_name":"Zhesong Yu","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":"Zhesong Yu","raw_affiliation_strings":["Wangxuan Institute of Computer Technology, Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wangxuan Institute of Computer Technology, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043937567","display_name":"Xiaoshuo Xu","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":"Xiaoshuo Xu","raw_affiliation_strings":["Wangxuan Institute of Computer Technology, Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wangxuan Institute of Computer Technology, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"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":["Wangxuan Institute of Computer Technology, Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wangxuan Institute of Computer Technology, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","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":["Wangxuan Institute of Computer Technology, Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wangxuan Institute of Computer Technology, Peking University","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":2.7934,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.92024725,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"541","last_page":"545"},"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":0.9944999814033508,"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":0.9797000288963318,"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":0.7765085697174072},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7283607125282288},{"id":"https://openalex.org/keywords/cover","display_name":"Cover (algebra)","score":0.6949166059494019},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6720620393753052},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6504485607147217},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5767305493354797},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5481477379798889},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5149505734443665},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5069699287414551},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42713743448257446},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.4212658107280731},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38608241081237793},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.1623740792274475}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7765085697174072},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7283607125282288},{"id":"https://openalex.org/C2780428219","wikidata":"https://www.wikidata.org/wiki/Q16952335","display_name":"Cover (algebra)","level":2,"score":0.6949166059494019},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6720620393753052},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6504485607147217},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5767305493354797},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5481477379798889},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5149505734443665},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5069699287414551},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42713743448257446},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.4212658107280731},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38608241081237793},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.1623740792274475},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053839","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053839","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5299999713897705}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W807698299","https://openalex.org/W1486009449","https://openalex.org/W1686810756","https://openalex.org/W2062533814","https://openalex.org/W2101642281","https://openalex.org/W2131739315","https://openalex.org/W2137319814","https://openalex.org/W2154473523","https://openalex.org/W2191779130","https://openalex.org/W2194775991","https://openalex.org/W2374249993","https://openalex.org/W2408482937","https://openalex.org/W2538860156","https://openalex.org/W2587288237","https://openalex.org/W2605092535","https://openalex.org/W2611198916","https://openalex.org/W2740932163","https://openalex.org/W2772072643","https://openalex.org/W2896276533","https://openalex.org/W2903337088","https://openalex.org/W2962835968","https://openalex.org/W2965178495","https://openalex.org/W2991402284","https://openalex.org/W6622967950","https://openalex.org/W6637373629","https://openalex.org/W6682527865","https://openalex.org/W6708751865","https://openalex.org/W6714078465","https://openalex.org/W6729231832","https://openalex.org/W6736035150","https://openalex.org/W6737110982","https://openalex.org/W6746244618","https://openalex.org/W6756466442","https://openalex.org/W6764992649"],"related_works":["https://openalex.org/W4232403550","https://openalex.org/W623607250","https://openalex.org/W4245429118","https://openalex.org/W4205110281","https://openalex.org/W4212927854","https://openalex.org/W4211151614","https://openalex.org/W4244798043","https://openalex.org/W4361866086","https://openalex.org/W4251969024","https://openalex.org/W4250793136"],"abstract_inverted_index":{"Cover":[0],"song":[1,62,84],"identification":[2],"is":[3,76,89],"a":[4,54],"challenging":[5],"task":[6],"in":[7],"the":[8,36,66,74],"field":[9],"of":[10],"Music":[11],"Information":[12],"Retrieval":[13],"(MIR)":[14],"due":[15],"to":[16,78,91],"complex":[17],"musical":[18],"variations":[19],"between":[20],"query":[21],"tracks":[22],"and":[23,32],"cover":[24,61,83],"versions.":[25],"Previous":[26],"works":[27],"typically":[28],"utilize":[29],"hand-crafted":[30],"features":[31],"alignment":[33],"algorithms":[34],"for":[35,82],"task.":[37],"More":[38],"recently,":[39],"further":[40],"breakthroughs":[41],"are":[42],"achieved":[43],"by":[44],"employing":[45],"neural":[46],"network":[47,67,75],"approaches.":[48],"In":[49],"this":[50],"paper,":[51],"we":[52],"propose":[53],"novel":[55],"Convolutional":[56],"Neural":[57],"Network":[58],"(CNN)":[59],"towards":[60],"identification.":[63,85],"We":[64],"train":[65,92],"through":[68],"classification":[69],"criteria.":[70],"Having":[71],"been":[72],"trained,":[73],"used":[77],"extract":[79],"music":[80],"representation":[81],"A":[86],"training":[87],"scheme":[88],"designed":[90],"robust":[93],"models":[94],"against":[95],"tempo":[96],"changes.":[97],"Experimental":[98],"results":[99],"show":[100],"that":[101],"our":[102],"approach":[103],"outperforms":[104],"state-of-the-art":[105],"methods":[106],"on":[107],"several":[108],"public":[109],"datasets":[110],"with":[111],"low":[112],"time":[113],"complexity.":[114]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}