{"id":"https://openalex.org/W2906259846","doi":"https://doi.org/10.1109/msp.2018.2868887","title":"Cross-Modal Music Retrieval and Applications: An Overview of Key Methodologies","display_name":"Cross-Modal Music Retrieval and Applications: An Overview of Key Methodologies","publication_year":2018,"publication_date":"2018-12-25","ids":{"openalex":"https://openalex.org/W2906259846","doi":"https://doi.org/10.1109/msp.2018.2868887","mag":"2906259846"},"language":"en","primary_location":{"id":"doi:10.1109/msp.2018.2868887","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msp.2018.2868887","pdf_url":null,"source":{"id":"https://openalex.org/S120977877","display_name":"IEEE Signal Processing Magazine","issn_l":"1053-5888","issn":["1053-5888","1558-0792"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Magazine","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1902.04397","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059890342","display_name":"Meinard M\u00fceller","orcid":"https://orcid.org/0000-0001-6062-7524"},"institutions":[{"id":"https://openalex.org/I4210123192","display_name":"International Audio Laboratories Erlangen","ror":"https://ror.org/02mkz3e80","country_code":"DE","type":"facility","lineage":["https://openalex.org/I181369854","https://openalex.org/I4210123192","https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Meinard Mueller","raw_affiliation_strings":["International Audio Laboratories Erlangen, Erlangen, Germany"],"raw_orcid":"https://orcid.org/0000-0001-6062-7524","affiliations":[{"raw_affiliation_string":"International Audio Laboratories Erlangen, Erlangen, Germany","institution_ids":["https://openalex.org/I4210123192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033618490","display_name":"Andreas Arzt","orcid":"https://orcid.org/0000-0002-3373-6239"},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Andreas Arzt","raw_affiliation_strings":["Computational intelligence, Vienna University of Technology, Austria"],"raw_orcid":"https://orcid.org/0000-0002-3373-6239","affiliations":[{"raw_affiliation_string":"Computational intelligence, Vienna University of Technology, Austria","institution_ids":["https://openalex.org/I145847075"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078080260","display_name":"Stefan Balke","orcid":"https://orcid.org/0000-0003-1306-3548"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stefan Balke","raw_affiliation_strings":["Electrical engineering, Leibniz Universit\u00e4t, Hanover, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical engineering, Leibniz Universit\u00e4t, Hanover, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029203655","display_name":"Matthias Dorfer","orcid":"https://orcid.org/0000-0002-3806-5411"},"institutions":[{"id":"https://openalex.org/I121883995","display_name":"Johannes Kepler University of Linz","ror":"https://ror.org/052r2xn60","country_code":"AT","type":"education","lineage":["https://openalex.org/I121883995"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Matthias Dorfer","raw_affiliation_strings":["Department of Computational Perception, Johannes Kepler University, Linz, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computational Perception, Johannes Kepler University, Linz, Austria","institution_ids":["https://openalex.org/I121883995"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003768123","display_name":"Gerhard Widmer","orcid":"https://orcid.org/0000-0003-3531-1282"},"institutions":[{"id":"https://openalex.org/I121883995","display_name":"Johannes Kepler University of Linz","ror":"https://ror.org/052r2xn60","country_code":"AT","type":"education","lineage":["https://openalex.org/I121883995"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Gerhard Widmer","raw_affiliation_strings":["Department of Computational Perception, Johannes Kepler University, Linz, Austria"],"raw_orcid":"https://orcid.org/0000-0003-3531-1282","affiliations":[{"raw_affiliation_string":"Department of Computational Perception, Johannes Kepler University, Linz, Austria","institution_ids":["https://openalex.org/I121883995"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5059890342"],"corresponding_institution_ids":["https://openalex.org/I4210123192"],"apc_list":null,"apc_paid":null,"fwci":4.4874,"has_fulltext":false,"cited_by_count":62,"citation_normalized_percentile":{"value":0.95622676,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"36","issue":"1","first_page":"52","last_page":"62"},"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":0.9973000288009644,"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":0.9929999709129333,"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":0.8383177518844604},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.7245296835899353},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6245068907737732},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.6243836879730225},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5868801474571228},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5778578519821167},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.54266756772995},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.4752338230609894},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.46325263381004333},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4585104286670685},{"id":"https://openalex.org/keywords/clips","display_name":"CLIPS","score":0.435703843832016},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3401715159416199},{"id":"https://openalex.org/keywords/digital-audio","display_name":"Digital audio","score":0.3225530982017517},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.2744169235229492},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2728332281112671},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.08271092176437378}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8383177518844604},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.7245296835899353},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6245068907737732},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6243836879730225},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5868801474571228},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5778578519821167},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.54266756772995},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.4752338230609894},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.46325263381004333},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4585104286670685},{"id":"https://openalex.org/C2778739407","wikidata":"https://www.wikidata.org/wiki/Q165372","display_name":"CLIPS","level":2,"score":0.435703843832016},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3401715159416199},{"id":"https://openalex.org/C87687168","wikidata":"https://www.wikidata.org/wiki/Q173114","display_name":"Digital audio","level":4,"score":0.3225530982017517},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.2744169235229492},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2728332281112671},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.08271092176437378},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","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/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/msp.2018.2868887","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msp.2018.2868887","pdf_url":null,"source":{"id":"https://openalex.org/S120977877","display_name":"IEEE Signal Processing Magazine","issn_l":"1053-5888","issn":["1053-5888","1558-0792"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Magazine","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1902.04397","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1902.04397","pdf_url":"https://arxiv.org/pdf/1902.04397","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1902.04397","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1902.04397","pdf_url":"https://arxiv.org/pdf/1902.04397","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4441379325","display_name":null,"funder_award_id":"MU 2686/11-1","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G7650735049","display_name":null,"funder_award_id":"ERC-2014-AdG 670035","funder_id":"https://openalex.org/F4320338335","funder_display_name":"H2020 European Research Council"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320323031","display_name":"\u00d6sterreichische Forschungsf\u00f6rderungsgesellschaft","ror":"https://ror.org/028jc0449"},{"id":"https://openalex.org/F4320338335","display_name":"H2020 European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W170732776","https://openalex.org/W201136338","https://openalex.org/W1493535305","https://openalex.org/W1518164296","https://openalex.org/W1527575280","https://openalex.org/W1605342922","https://openalex.org/W1988749582","https://openalex.org/W2000304248","https://openalex.org/W2030511115","https://openalex.org/W2047411082","https://openalex.org/W2076063813","https://openalex.org/W2101722322","https://openalex.org/W2105143211","https://openalex.org/W2130865646","https://openalex.org/W2150555104","https://openalex.org/W2152937398","https://openalex.org/W2157590796","https://openalex.org/W2198584637","https://openalex.org/W2240711917","https://openalex.org/W2293877021","https://openalex.org/W2296463171","https://openalex.org/W2334757619","https://openalex.org/W2402674850","https://openalex.org/W2407125604","https://openalex.org/W2407410673","https://openalex.org/W2478051194","https://openalex.org/W2522234776","https://openalex.org/W2620341577","https://openalex.org/W2741600211","https://openalex.org/W2791904037","https://openalex.org/W2963720346","https://openalex.org/W3021908862","https://openalex.org/W3102718214","https://openalex.org/W4298399510","https://openalex.org/W6604987197","https://openalex.org/W6608257652","https://openalex.org/W6631516269","https://openalex.org/W6690107225","https://openalex.org/W6697209620","https://openalex.org/W6697479953","https://openalex.org/W6713401134","https://openalex.org/W6714145617","https://openalex.org/W6742368143"],"related_works":["https://openalex.org/W4248908904","https://openalex.org/W4382119215","https://openalex.org/W1552522012","https://openalex.org/W153728371","https://openalex.org/W627539891","https://openalex.org/W4237593738","https://openalex.org/W4230436760","https://openalex.org/W2363106653","https://openalex.org/W4251828160","https://openalex.org/W296599067"],"abstract_inverted_index":{"There":[0],"has":[1],"been":[2],"a":[3,45,52,60,66],"rapid":[4],"growth":[5],"of":[6,16,30,81,97],"digitally":[7],"available":[8],"music":[9,42],"data,":[10],"including":[11],"audio":[12,68,92],"recordings,":[13],"digitized":[14],"images":[15],"sheet":[17,86],"music,":[18],"album":[19],"covers":[20],"and":[21,24,73,84,94],"liner":[22],"notes,":[23],"video":[25],"clips.":[26],"This":[27,88],"huge":[28],"amount":[29],"data":[31],"calls":[32],"for":[33,54],"retrieval":[34,56,96],"strategies":[35],"that":[36],"allow":[37],"users":[38],"to":[39],"explore":[40],"large":[41],"collections":[43],"in":[44,62,75],"convenient":[46],"way.":[47],"More":[48],"precisely,":[49],"there":[50],"is":[51],"need":[53],"cross-modal":[55],"algorithms":[57],"that,":[58],"given":[59],"query":[61],"one":[63],"modality":[64],"(e.g.,":[65,78],"short":[67],"excerpt),":[69],"find":[70],"corresponding":[71],"information":[72],"entities":[74],"other":[76],"modalities":[77],"the":[79,82,85],"name":[80],"piece":[83],"music).":[87],"goes":[89],"beyond":[90],"exact":[91],"identification":[93],"subsequent":[95],"metainformation":[98],"as":[99],"performed":[100],"by":[101],"commercial":[102],"applications":[103],"like":[104],"Shazam":[105],"[1].":[106]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":7}],"updated_date":"2026-05-08T15:41:06.802602","created_date":"2019-01-01T00:00:00"}
