{"id":"https://openalex.org/W2016136491","doi":"https://doi.org/10.1109/tasl.2011.2172423","title":"A Generative Context Model for Semantic Music Annotation and Retrieval","display_name":"A Generative Context Model for Semantic Music Annotation and Retrieval","publication_year":2011,"publication_date":"2011-10-17","ids":{"openalex":"https://openalex.org/W2016136491","doi":"https://doi.org/10.1109/tasl.2011.2172423","mag":"2016136491"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2011.2172423","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2011.2172423","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"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 Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5001694059","display_name":"Riccardo Miotto","orcid":"https://orcid.org/0000-0002-7815-6000"},"institutions":[{"id":"https://openalex.org/I138689650","display_name":"University of Padua","ror":"https://ror.org/00240q980","country_code":"IT","type":"education","lineage":["https://openalex.org/I138689650"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Riccardo Miotto","raw_affiliation_strings":["Department of Information Engineering, University of Padova, Padova, Italy","Department of Information Engineering; University of Padova; Padova; Italy"],"affiliations":[{"raw_affiliation_string":"Department of Information Engineering, University of Padova, Padova, Italy","institution_ids":["https://openalex.org/I138689650"]},{"raw_affiliation_string":"Department of Information Engineering; University of Padova; Padova; Italy","institution_ids":["https://openalex.org/I138689650"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003709708","display_name":"Gert Lanckriet","orcid":null},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]},{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gert Lanckriet","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of California, San Diego, La Jolla, CA, USA","[Dept. of Electr. & Comput. Eng., Univ. of California, La Jolla, CA, USA]"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of California, San Diego, La Jolla, CA, USA","institution_ids":["https://openalex.org/I36258959"]},{"raw_affiliation_string":"[Dept. of Electr. & Comput. Eng., Univ. of California, La Jolla, CA, USA]","institution_ids":["https://openalex.org/I161318765"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5001694059"],"corresponding_institution_ids":["https://openalex.org/I138689650"],"apc_list":null,"apc_paid":null,"fwci":4.6793,"has_fulltext":false,"cited_by_count":41,"citation_normalized_percentile":{"value":0.95354285,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"20","issue":"4","first_page":"1096","last_page":"1108"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9952999949455261,"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":0.9904000163078308,"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":0.8285763263702393},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5782702565193176},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5692936182022095},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5466679334640503},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5081865787506104},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4926939308643341},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.49075230956077576},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4536837339401245},{"id":"https://openalex.org/keywords/bass","display_name":"Bass (fish)","score":0.4413129985332489},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.40997448563575745},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.184166818857193}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8285763263702393},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5782702565193176},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5692936182022095},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5466679334640503},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5081865787506104},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4926939308643341},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.49075230956077576},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4536837339401245},{"id":"https://openalex.org/C2777182073","wikidata":"https://www.wikidata.org/wiki/Q1224135","display_name":"Bass (fish)","level":2,"score":0.4413129985332489},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40997448563575745},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.184166818857193},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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":2,"locations":[{"id":"doi:10.1109/tasl.2011.2172423","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2011.2172423","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"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 Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.297.672","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.297.672","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cosmal.ucsd.edu/~gert/papers/gcm.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5699999928474426}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W15066456","https://openalex.org/W190008395","https://openalex.org/W1502275556","https://openalex.org/W1532325895","https://openalex.org/W1549656520","https://openalex.org/W1562529351","https://openalex.org/W1583199729","https://openalex.org/W1601795611","https://openalex.org/W1618905105","https://openalex.org/W1663973292","https://openalex.org/W1666447063","https://openalex.org/W1934863104","https://openalex.org/W2001014535","https://openalex.org/W2020842694","https://openalex.org/W2029109699","https://openalex.org/W2046390908","https://openalex.org/W2049633694","https://openalex.org/W2056507581","https://openalex.org/W2083383166","https://openalex.org/W2091158010","https://openalex.org/W2108672713","https://openalex.org/W2110306668","https://openalex.org/W2113229563","https://openalex.org/W2116373735","https://openalex.org/W2125238156","https://openalex.org/W2127119819","https://openalex.org/W2128197086","https://openalex.org/W2133824856","https://openalex.org/W2140013053","https://openalex.org/W2146632282","https://openalex.org/W2150692003","https://openalex.org/W2153635508","https://openalex.org/W2154016477","https://openalex.org/W2156336347","https://openalex.org/W2162124943","https://openalex.org/W2163614729","https://openalex.org/W2170076209","https://openalex.org/W2295268182","https://openalex.org/W2396710586","https://openalex.org/W3120421331","https://openalex.org/W3146463283","https://openalex.org/W4213009331","https://openalex.org/W4248892431","https://openalex.org/W6600593648","https://openalex.org/W6629949262","https://openalex.org/W6633698201","https://openalex.org/W6634842559","https://openalex.org/W6637249095","https://openalex.org/W6676823600","https://openalex.org/W6678865028","https://openalex.org/W6680873201","https://openalex.org/W6681980626","https://openalex.org/W6683737379","https://openalex.org/W6683915439","https://openalex.org/W6697340004","https://openalex.org/W6712494662"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W2280377497","https://openalex.org/W4387506531","https://openalex.org/W4238433571","https://openalex.org/W3174044702","https://openalex.org/W2967848559","https://openalex.org/W4283803360"],"abstract_inverted_index":{"While":[0],"a":[1,31,58,81,96,101,107,115,157],"listener":[2],"may":[3],"derive":[4],"semantic":[5,97],"associations":[6],"for":[7,37],"audio":[8],"clips":[9],"from":[10,21],"direct":[11],"auditory":[12],"cues":[13],"(e.g.,":[14,23],"hearing":[15],"\u201cbass":[16,25],"guitar\u201d)":[17],"as":[18,20,80,174],"well":[19],"\u201ccontext\u201d":[22],"inferring":[24],"guitar\u201d":[26],"in":[27,85,112,129],"the":[28,86,113,118,121,130,136,141,153],"context":[29,120,164,173],"of":[30,103,132,155,159],"\u201crock\u201d":[32],"song),":[33],"most":[34],"state-of-the-art":[35],"systems":[36],"automatic":[38,64],"music":[39,65],"annotation":[40,66],"ignore":[41],"this":[42,162],"context.":[43],"Indeed,":[44],"although":[45],"contextual":[46,69,148],"relationships":[47,70],"correlate":[48],"tags,":[49],"many":[50],"auto-taggers":[51,160],"model":[52,76],"tags":[53,104],"independently.":[54],"This":[55],"paper":[56],"presents":[57],"novel,":[59],"generative":[60,163],"approach":[61],"to":[62,89,171],"improve":[63],"by":[67,124,146],"modeling":[68,87,125,172],"between":[71],"tags.":[72],"A":[73],"Dirichlet":[74],"mixture":[75],"(DMM)":[77],"is":[78],"proposed":[79],"second,":[82],"additional":[83],"stage":[84],"process,":[88],"supplement":[90],"any":[91],"auto-tagging":[92],"system":[93],"that":[94],"generates":[95],"multinomial":[98],"(SMN)":[99],"over":[100],"vocabulary":[102],"when":[105],"annotating":[106,139],"song.":[108],"For":[109],"each":[110],"tag":[111,122,126],"vocabulary,":[114],"DMM":[116],"captures":[117],"broader":[119],"defines":[123],"co-occurrence":[127],"patterns":[128],"SMNs":[131],"songs":[133],"associated":[134],"with":[135,161],"tag.":[137],"When":[138],"songs,":[140],"DMMs":[142],"refine":[143],"SMN":[144],"annotations":[145],"leveraging":[147],"evidence.":[149],"Experimental":[150],"results":[151],"demonstrate":[152],"benefits":[154],"combining":[156],"variety":[158],"model.":[165],"It":[166],"generally":[167],"outperforms":[168],"other":[169],"approaches":[170],"well.":[175]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}