{"id":"https://openalex.org/W2059377701","doi":"https://doi.org/10.1145/2324796.2324834","title":"Musical keys and chords recognition using unsupervised learning with infinite Gaussian mixture","display_name":"Musical keys and chords recognition using unsupervised learning with infinite Gaussian mixture","publication_year":2012,"publication_date":"2012-06-05","ids":{"openalex":"https://openalex.org/W2059377701","doi":"https://doi.org/10.1145/2324796.2324834","mag":"2059377701"},"language":"en","primary_location":{"id":"doi:10.1145/2324796.2324834","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2324796.2324834","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd ACM International Conference on Multimedia Retrieval","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/A5101459077","display_name":"Yunsheng Wang","orcid":"https://orcid.org/0009-0002-6832-9518"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yun-Sheng Wang","raw_affiliation_strings":["George Mason University"],"affiliations":[{"raw_affiliation_string":"George Mason University","institution_ids":["https://openalex.org/I162714631"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058156010","display_name":"Harry Wechsler","orcid":"https://orcid.org/0000-0002-5454-8819"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Harry Wechsler","raw_affiliation_strings":["George Mason University"],"affiliations":[{"raw_affiliation_string":"George Mason University","institution_ids":["https://openalex.org/I162714631"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101459077"],"corresponding_institution_ids":["https://openalex.org/I162714631"],"apc_list":null,"apc_paid":null,"fwci":0.2448,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.54879146,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"1","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9764000177383423,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9724000096321106,"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/chord","display_name":"Chord (peer-to-peer)","score":0.7838143110275269},{"id":"https://openalex.org/keywords/midi","display_name":"MIDI","score":0.7224596738815308},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6870450377464294},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5900008082389832},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.5143746137619019},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5123621225357056},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.49624067544937134},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.4655030369758606},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.43133342266082764},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4312005341053009},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.39092719554901123},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34842902421951294}],"concepts":[{"id":"https://openalex.org/C194147245","wikidata":"https://www.wikidata.org/wiki/Q1076368","display_name":"Chord (peer-to-peer)","level":2,"score":0.7838143110275269},{"id":"https://openalex.org/C8112396","wikidata":"https://www.wikidata.org/wiki/Q80535","display_name":"MIDI","level":2,"score":0.7224596738815308},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6870450377464294},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5900008082389832},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.5143746137619019},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5123621225357056},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.49624067544937134},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.4655030369758606},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.43133342266082764},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4312005341053009},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.39092719554901123},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34842902421951294},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2324796.2324834","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2324796.2324834","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd ACM International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W4928837","https://openalex.org/W143721997","https://openalex.org/W1485787479","https://openalex.org/W1540613698","https://openalex.org/W1549135121","https://openalex.org/W1967687583","https://openalex.org/W1972684956","https://openalex.org/W2016503548","https://openalex.org/W2018738723","https://openalex.org/W2024595034","https://openalex.org/W2037874181","https://openalex.org/W2042978954","https://openalex.org/W2045034970","https://openalex.org/W2069429561","https://openalex.org/W2080972498","https://openalex.org/W2089484716","https://openalex.org/W2111007352","https://openalex.org/W2120636621","https://openalex.org/W2128309385","https://openalex.org/W2150319510","https://openalex.org/W2152756914","https://openalex.org/W2160484251","https://openalex.org/W2319171828","https://openalex.org/W4212774754","https://openalex.org/W4285719527","https://openalex.org/W4312640348","https://openalex.org/W6656746481","https://openalex.org/W6661665707","https://openalex.org/W6678007500"],"related_works":["https://openalex.org/W3133630535","https://openalex.org/W2398084541","https://openalex.org/W4285232104","https://openalex.org/W4242364395","https://openalex.org/W2022907688","https://openalex.org/W4226108805","https://openalex.org/W3215960001","https://openalex.org/W4307957021","https://openalex.org/W1992295166","https://openalex.org/W2143508933"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,24],"Bayesian-based":[4],"methodology":[5],"that":[6,115],"determines":[7],"keys":[8,38,65,123],"and":[9,39,42,50,66,124],"chords":[10,43,67,125],"of":[11,26,37,76,86,94],"symbolic":[12],"music":[13],"using":[14,53,104],"unsupervised":[15],"learning":[16,71],"guided":[17],"by":[18,47,98],"constraints.":[19],"An":[20],"infinite":[21],"Gaussian":[22],"mixture,":[23,29],"type":[25],"Dirichlet":[27],"Process":[28],"is":[30,83],"constructed":[31],"to":[32,68],"model":[33,58],"the":[34,54,70,74,92,95,108,116],"generative":[35],"processes":[36],"chords.":[40],"Keys":[41],"are":[44],"recognized":[45],"iteratively":[46],"generated":[48],"key":[49,88],"chord":[51],"samples":[52],"same":[55],"algorithm.":[56],"The":[57,81,112],"only":[59],"uses":[60],"very":[61],"simple":[62],"profiles":[63],"for":[64],"guide":[69],"process":[72],"without":[73],"use":[75],"training":[77],"data":[78],"or":[79],"rules.":[80],"technique":[82],"also":[84],"capable":[85],"recognizing":[87],"modulations.":[89],"We":[90],"demonstrate":[91],"performance":[93],"proposed":[96,117],"approach":[97],"comparing":[99],"it":[100],"against":[101],"existing":[102],"methods":[103],"159":[105],"songs":[106],"from":[107],"Beatles":[109],"MIDI":[110],"collection.":[111],"results":[113],"show":[114],"method":[118],"performs":[119],"well":[120],"in":[121],"both":[122],"finding.":[126]},"counts_by_year":[{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}