{"id":"https://openalex.org/W2083383166","doi":"https://doi.org/10.1145/1743384.1743400","title":"Exploring automatic music annotation with \"acoustically-objective\" tags","display_name":"Exploring automatic music annotation with \"acoustically-objective\" tags","publication_year":2010,"publication_date":"2010-03-29","ids":{"openalex":"https://openalex.org/W2083383166","doi":"https://doi.org/10.1145/1743384.1743400","mag":"2083383166"},"language":"en","primary_location":{"id":"doi:10.1145/1743384.1743400","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1743384.1743400","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the international conference on Multimedia information retrieval","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/A5028348481","display_name":"Derek Tingle","orcid":null},"institutions":[{"id":"https://openalex.org/I118020396","display_name":"Swarthmore College","ror":"https://ror.org/012dg8a96","country_code":"US","type":"education","lineage":["https://openalex.org/I118020396"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Derek Tingle","raw_affiliation_strings":["Swarthmore College, Swarthmore, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Swarthmore College, Swarthmore, PA, USA","institution_ids":["https://openalex.org/I118020396"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025175604","display_name":"Youngmoo E. Kim","orcid":"https://orcid.org/0009-0005-0922-1787"},"institutions":[{"id":"https://openalex.org/I72816309","display_name":"Drexel University","ror":"https://ror.org/04bdffz58","country_code":"US","type":"education","lineage":["https://openalex.org/I72816309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Youngmoo E. Kim","raw_affiliation_strings":["Drexel University, Philadelphia, PA, USA","Drexel University, Philadelphia, PA, USA;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Drexel University, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I72816309"]},{"raw_affiliation_string":"Drexel University, Philadelphia, PA, USA;","institution_ids":["https://openalex.org/I72816309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005989028","display_name":"Douglas Turnbull","orcid":"https://orcid.org/0009-0001-7252-1855"},"institutions":[{"id":"https://openalex.org/I118020396","display_name":"Swarthmore College","ror":"https://ror.org/012dg8a96","country_code":"US","type":"education","lineage":["https://openalex.org/I118020396"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Douglas Turnbull","raw_affiliation_strings":["Swarthmore College, Swarthmore, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Swarthmore College, Swarthmore, PA, USA","institution_ids":["https://openalex.org/I118020396"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":12.1647,"has_fulltext":false,"cited_by_count":85,"citation_normalized_percentile":{"value":0.99326599,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"55","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":0.9973999857902527,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9919999837875366,"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":0.7933721542358398},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.6201115250587463},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.6102166771888733},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.5581600069999695},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5485790371894836},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5268710255622864},{"id":"https://openalex.org/keywords/loudness","display_name":"Loudness","score":0.50922691822052},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4989945888519287},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.48421764373779297},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4636361002922058},{"id":"https://openalex.org/keywords/echo","display_name":"Echo (communications protocol)","score":0.4401094615459442},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.42918145656585693},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.41131314635276794},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.41106122732162476},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.407022625207901},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3870491683483124},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36073797941207886},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.22036606073379517},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.08246585726737976}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7933721542358398},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.6201115250587463},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.6102166771888733},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.5581600069999695},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5485790371894836},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5268710255622864},{"id":"https://openalex.org/C79018884","wikidata":"https://www.wikidata.org/wiki/Q622324","display_name":"Loudness","level":2,"score":0.50922691822052},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4989945888519287},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.48421764373779297},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4636361002922058},{"id":"https://openalex.org/C2779426996","wikidata":"https://www.wikidata.org/wiki/Q18389128","display_name":"Echo (communications protocol)","level":2,"score":0.4401094615459442},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.42918145656585693},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.41131314635276794},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.41106122732162476},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.407022625207901},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3870491683483124},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36073797941207886},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.22036606073379517},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.08246585726737976},{"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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1743384.1743400","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1743384.1743400","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the international conference on Multimedia information retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.306.9746","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.306.9746","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://web.cs.swarthmore.edu/~turnbull/Papers/Tingle_Autotag_MIR10.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5699999928474426,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W15066456","https://openalex.org/W22907347","https://openalex.org/W168014444","https://openalex.org/W1493526108","https://openalex.org/W1507955343","https://openalex.org/W1532325895","https://openalex.org/W1549656520","https://openalex.org/W1560013842","https://openalex.org/W1576445103","https://openalex.org/W1618905105","https://openalex.org/W1666447063","https://openalex.org/W1988790447","https://openalex.org/W2001014535","https://openalex.org/W2067329295","https://openalex.org/W2074530091","https://openalex.org/W2109607073","https://openalex.org/W2116373735","https://openalex.org/W2133824856","https://openalex.org/W2133999183","https://openalex.org/W2136564616","https://openalex.org/W2140013053","https://openalex.org/W2162124943","https://openalex.org/W2404937750"],"related_works":["https://openalex.org/W1970025505","https://openalex.org/W2030358499","https://openalex.org/W1966585405","https://openalex.org/W1107690805","https://openalex.org/W2097318409","https://openalex.org/W2739662815","https://openalex.org/W1481643945","https://openalex.org/W2153275212","https://openalex.org/W2402674073","https://openalex.org/W2328848613"],"abstract_inverted_index":{"The":[0,75,120],"task":[1],"of":[2,56,63,109,132,148,168,192],"automatically":[3],"annotating":[4],"music":[5,20,149],"with":[6,105,137],"text":[7],"tags":[8,66,77],"(referred":[9],"to":[10,15,28,39,87,199,217,220],"as":[11],"autotagging)":[12],"is":[13,165],"vital":[14],"creating":[16],"a":[17,31,49,61,127,130,144,166],"large-scale":[18],"semantic":[19],"discovery":[21],"engine.":[22],"Yet":[23],"for":[24],"an":[25,94],"autotagging":[26,95,152,225],"system":[27],"be":[29,84,215],"successful,":[30],"large":[32],"and":[33,67,150,205,222],"cleanly-annotated":[34],"data":[35,50,101],"set":[36,102],"must":[37],"exist":[38],"train":[40],"the":[41,99,115,157,179,186,190],"system.":[42],"For":[43],"this":[44],"reason,":[45],"we":[46,97,197],"have":[47],"collected":[48],"set,":[51],"called":[52],"Swat10k,":[53],"which":[54,164],"consists":[55],"10,870":[57],"songs":[58,88],"annotated":[59],"using":[60,114,129],"vocabulary":[62],"475":[64],"acoustic":[65,76,170],"153":[68],"genre":[69],"tags}from":[70],"Pandora's":[71],"Music":[72],"Genome":[73],"Project.":[74],"are":[78],"considered":[79],"\"acoustically-objective\"":[80],"because":[81],"they":[82,188],"can":[83],"consistently":[85],"applied":[86],"by":[89],"expert":[90],"musicologists.":[91],"To":[92],"develop":[93,221],"system,":[96],"use":[98,218],"Swat10k":[100],"in":[103],"conjunction":[104],"two":[106],"new":[107],"sets":[108],"content-based":[110],"audio":[111],"features":[112,125,171,181,209],"obtained":[113],"publicly-available":[116],"Echo":[117,121,158,207],"Nest":[118,122,159,208],"API.":[119],"Timbre":[123],"(ENT)":[124],"represent":[126],"song":[128,203],"collection":[131,167],"short-time":[133],"feature":[134,162],"vectors.":[135],"Compared":[136],"Mel-frequency":[138],"cepstral":[139],"coefficients":[140],"(MFCCs),":[141],"ENTs":[142],"provide":[143],"more":[145],"compact":[146],"representation":[147],"improve":[151],"performance.":[153],"We":[154],"also":[155],"evaluate":[156],"Song":[160],"(ENS)":[161],"vector,":[163],"mid-level":[169],"(e.g.,":[172],"beats":[173],"per":[174],"minute,":[175],"average":[176],"loudness).":[177],"While":[178],"ENS":[180],"generally":[182],"perform":[183],"worse":[184],"than":[185],"ENTs,":[187],"increase":[189],"performance":[191],"several":[193],"individual":[194],"tags.":[195],"Furthermore,":[196],"plan":[198],"publicly":[200],"release":[201],"our":[202],"annotations":[204],"corresponding":[206],"so":[210],"that":[211],"other":[212],"researchers":[213],"will":[214],"able":[216],"Swat10K":[219],"compare":[223],"alternative":[224],"algorithms.":[226]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":10},{"year":2013,"cited_by_count":14},{"year":2012,"cited_by_count":12}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}