{"id":"https://openalex.org/W2152491694","doi":"https://doi.org/10.1145/2393347.2393367","title":"The acoustic emotion gaussians model for emotion-based music annotation and retrieval","display_name":"The acoustic emotion gaussians model for emotion-based music annotation and retrieval","publication_year":2012,"publication_date":"2012-10-29","ids":{"openalex":"https://openalex.org/W2152491694","doi":"https://doi.org/10.1145/2393347.2393367","mag":"2152491694"},"language":"en","primary_location":{"id":"doi:10.1145/2393347.2393367","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2393347.2393367","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM international conference on Multimedia","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/A5065288078","display_name":"Ju-Chiang Wang","orcid":"https://orcid.org/0009-0002-8265-4229"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ju-Chiang Wang","raw_affiliation_strings":["National Taiwan University, Taipei City, Taiwan Roc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University, Taipei City, Taiwan Roc","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061291906","display_name":"Yi\u2010Hsuan Yang","orcid":"https://orcid.org/0000-0002-2724-6161"},"institutions":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yi-Hsuan Yang","raw_affiliation_strings":["Academia Sinica, Taipei City, Taiwan Roc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academia Sinica, Taipei City, Taiwan Roc","institution_ids":["https://openalex.org/I84653119"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071214181","display_name":"Hsin\u2010Min Wang","orcid":"https://orcid.org/0000-0003-3599-5071"},"institutions":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsin-Min Wang","raw_affiliation_strings":["Academia Sinica, Taipei City, Taiwan Roc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academia Sinica, Taipei City, Taiwan Roc","institution_ids":["https://openalex.org/I84653119"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028285867","display_name":"Shyh\u2010Kang Jeng","orcid":"https://orcid.org/0000-0001-8960-9995"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Shyh-Kang Jeng","raw_affiliation_strings":["National Taiwan University, Taipei City, Taiwan Roc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University, Taipei City, Taiwan Roc","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":67,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"89","last_page":"98"},"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":0.9987999796867371,"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":0.996399998664856,"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":0.7259259223937988},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5450423955917358},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5288825035095215},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.515130877494812},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5139734148979187},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.509891152381897},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5080411434173584},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4597390592098236},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.43876829743385315},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3660431504249573},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36475834250450134},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1310105323791504},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07993918657302856}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7259259223937988},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5450423955917358},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5288825035095215},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.515130877494812},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5139734148979187},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.509891152381897},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5080411434173584},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4597390592098236},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.43876829743385315},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3660431504249573},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36475834250450134},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1310105323791504},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07993918657302856},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","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},{"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:10.1145/2393347.2393367","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2393347.2393367","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM international conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.676.3728","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.676.3728","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.iis.sinica.edu.tw/papers/asriver/2458-F.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6200000047683716,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321040","display_name":"National Science Council","ror":"https://ror.org/02kv4zf79"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W207683342","https://openalex.org/W625810977","https://openalex.org/W858155270","https://openalex.org/W1506806321","https://openalex.org/W1521253151","https://openalex.org/W1601795611","https://openalex.org/W1663973292","https://openalex.org/W1855693260","https://openalex.org/W1868379447","https://openalex.org/W1994477474","https://openalex.org/W1999209640","https://openalex.org/W2008133390","https://openalex.org/W2028443633","https://openalex.org/W2033178790","https://openalex.org/W2069870183","https://openalex.org/W2089705003","https://openalex.org/W2097705935","https://openalex.org/W2117645142","https://openalex.org/W2134249015","https://openalex.org/W2134305421","https://openalex.org/W2135475818","https://openalex.org/W2141517887","https://openalex.org/W2148600927","https://openalex.org/W2149628368","https://openalex.org/W2153777989","https://openalex.org/W2160929029","https://openalex.org/W2161920802","https://openalex.org/W2163147858","https://openalex.org/W2171848217","https://openalex.org/W2294891765","https://openalex.org/W2296587773","https://openalex.org/W2341090665","https://openalex.org/W2408751413","https://openalex.org/W3217467030","https://openalex.org/W6629510986","https://openalex.org/W6629902391","https://openalex.org/W6682769614","https://openalex.org/W6704344484"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W2280377497","https://openalex.org/W3174044702","https://openalex.org/W4238433571","https://openalex.org/W2967848559","https://openalex.org/W4283803360","https://openalex.org/W4317695495","https://openalex.org/W4387506531"],"abstract_inverted_index":{"One":[0],"of":[1,22,51,66,83,108,138,154,192],"the":[2,19,67,73,96,101,106,112,131,139,151,172,176,186],"most":[3],"exciting":[4],"but":[5],"challenging":[6],"endeavors":[7],"in":[8,54,179],"music":[9,23,28,78,120,125,163,181,194],"research":[10],"is":[11,92,115,147,196],"to":[12,31,94,117,149],"develop":[13],"a":[14,27,38,47,57,81,189],"computational":[15],"model":[16,44,68,114,140,174],"that":[17,45,171],"comprehends":[18],"affective":[20],"content":[21],"signals":[24],"and":[25,63,77,123,166],"organizes":[26],"collection":[29],"according":[30],"emotion.":[32],"In":[33],"this":[34],"paper,":[35],"we":[36,134],"propose":[37],"novel":[39],"acoustic":[40,74],"emotion":[41,52,79,121,161,182],"Gaussians":[42],"(AEG)":[43],"defines":[46],"proper":[48],"generative":[49,58],"process":[50],"perception":[53],"music.":[55],"As":[56],"model,":[59,133],"AEG":[60,113,132,155,173],"permits":[61],"easy":[62],"straightforward":[64],"interpretations":[65],"learning":[69,141],"processes.":[70],"To":[71,127],"bridge":[72],"feature":[75,85,110],"space":[76,107],"space,":[80],"set":[82],"latent":[84,109],"classes,":[86,111],"which":[87],"are":[88],"learned":[89],"from":[90],"data,":[91],"introduced":[93],"perform":[95],"end-to-end":[97],"semantic":[98],"mappings":[99],"between":[100],"two":[102,160],"spaces.":[103],"Based":[104],"on":[105],"applicable":[116],"both":[118],"automatic":[119,180],"annotation":[122],"emotion-based":[124,193],"retrieval.":[126],"gain":[128],"insights":[129],"into":[130],"also":[135],"provide":[136],"illustrations":[137],"process.":[142],"A":[143],"comprehensive":[144],"performance":[145],"study":[146],"conducted":[148],"demonstrate":[150],"superior":[152],"accuracy":[153],"over":[156],"its":[157],"predecessors,":[158],"using":[159],"annotated":[162],"corpora":[164],"MER60":[165],"MTurk.":[167],"Our":[168],"results":[169],"show":[170],"outperforms":[175],"state-of-the-art":[177],"methods":[178],"annotation.":[183],"Moreover,":[184],"for":[185],"first":[187],"time":[188],"quantitative":[190],"evaluation":[191],"retrieval":[195],"reported.":[197]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":10},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}