{"id":"https://openalex.org/W2163966202","doi":"https://doi.org/10.1109/icme.2010.5583009","title":"Homogeneous segmentation and classifier ensemble for audio tag annotation and retrieval","display_name":"Homogeneous segmentation and classifier ensemble for audio tag annotation and retrieval","publication_year":2010,"publication_date":"2010-07-01","ids":{"openalex":"https://openalex.org/W2163966202","doi":"https://doi.org/10.1109/icme.2010.5583009","mag":"2163966202"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2010.5583009","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2010.5583009","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Multimedia and Expo","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/A5102235147","display_name":"Hung-Yi Lo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hung-Yi Lo","raw_affiliation_strings":["Institute of Information Science, Academia Sinica, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065288078","display_name":"Ju-Chiang Wang","orcid":"https://orcid.org/0009-0002-8265-4229"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ju-Chiang Wang","raw_affiliation_strings":["Institute of Information Science, Academia Sinica, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071214181","display_name":"Hsin\u2010Min Wang","orcid":"https://orcid.org/0000-0003-3599-5071"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsin-Min Wang","raw_affiliation_strings":["Institute of Information Science, Academia Sinica, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210098366"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"5021","issue":null,"first_page":"304","last_page":"309"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9968000054359436,"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":0.991599977016449,"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":0.800097644329071},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6191897392272949},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5312228798866272},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5229790210723877},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.4908042848110199},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.48696526885032654},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.47821900248527527},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4537986218929291},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.4497607946395874},{"id":"https://openalex.org/keywords/adaboost","display_name":"AdaBoost","score":0.4471191465854645},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.09548404812812805}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.800097644329071},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6191897392272949},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5312228798866272},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5229790210723877},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.4908042848110199},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.48696526885032654},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.47821900248527527},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4537986218929291},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.4497607946395874},{"id":"https://openalex.org/C141404830","wikidata":"https://www.wikidata.org/wiki/Q2823869","display_name":"AdaBoost","level":3,"score":0.4471191465854645},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.09548404812812805},{"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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icme.2010.5583009","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2010.5583009","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Multimedia and Expo","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.675.3366","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.675.3366","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/404-F.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5400000214576721}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W168039245","https://openalex.org/W1508121828","https://openalex.org/W1618905105","https://openalex.org/W1979955134","https://openalex.org/W1988790447","https://openalex.org/W2056983531","https://openalex.org/W2071913706","https://openalex.org/W2098580349","https://openalex.org/W2113229563","https://openalex.org/W2116373735","https://openalex.org/W2139238328","https://openalex.org/W2140013053","https://openalex.org/W2162124943","https://openalex.org/W2167969117","https://openalex.org/W6606829919","https://openalex.org/W6630222583","https://openalex.org/W6668475982","https://openalex.org/W6674927801","https://openalex.org/W6676823600","https://openalex.org/W6680873201","https://openalex.org/W6683737379"],"related_works":["https://openalex.org/W2406877384","https://openalex.org/W2595839522","https://openalex.org/W2124576126","https://openalex.org/W2138455584","https://openalex.org/W1984264321","https://openalex.org/W1481643945","https://openalex.org/W2153275212","https://openalex.org/W2402674073","https://openalex.org/W2328848613","https://openalex.org/W1985186561"],"abstract_inverted_index":{"Audio":[0],"tags":[1,23],"describe":[2],"different":[3],"types":[4],"of":[5,116,174],"musical":[6,63],"information":[7],"such":[8,65,90,139],"as":[9,66],"genre,":[10],"mood,":[11],"and":[12,24,51,71,87,118,166,176],"instrument.":[13],"This":[14],"paper":[15],"aims":[16],"to":[17,61,100],"automatically":[18],"annotate":[19],"audio":[20,36,48,54,126,148,162],"clips":[21,27],"with":[22,59,96],"retrieve":[25],"relevant":[26],"from":[28,56],"a":[29,102,107,184],"music":[30],"database":[31],"by":[32,45,84],"tags.":[33],"Given":[34],"an":[35,47,111],"clip,":[37],"we":[38,151],"divide":[39],"it":[40],"into":[41,135],"several":[42],"homogeneous":[43],"segments":[44],"using":[46,153],"novelty":[49],"curve,":[50],"then":[52],"extract":[53],"features":[55,74,99],"each":[57,122],"segment":[58],"respect":[60],"various":[62],"information,":[64],"dynamics,":[67],"rhythm,":[68],"timbre,":[69],"pitch,":[70],"tonality.":[72],"The":[73],"in":[75,158,172],"frame-based":[76],"feature":[77,104],"vector":[78,105],"sequence":[79],"format":[80],"are":[81,133],"further":[82],"represented":[83],"their":[85],"mean":[86],"standard":[88],"deviation":[89],"that":[91,140],"they":[92],"can":[93,143],"be":[94,144],"combined":[95],"other":[97],"segment-based":[98],"form":[101],"fixed-dimensional":[103],"for":[106,121],"segment.":[108],"We":[109,156],"train":[110],"ensemble":[112,142],"classifier,":[113],"which":[114],"consists":[115],"SVM":[117],"AdaBoost":[119],"classifiers,":[120],"tag.":[123,185],"For":[124,146],"the":[125,129,147,159,177,180],"annotation":[127],"task,":[128,150],"individual":[130],"classifier":[131],"outputs":[132],"transformed":[134],"calibrated":[136],"probability":[137,141],"scores":[138],"employed.":[145],"retrieval":[149],"propose":[152],"ranking":[154],"ensemble.":[155],"participated":[157],"MIREX":[160],"2009":[161],"tag":[163],"classification":[164],"task":[165],"our":[167],"system":[168],"was":[169],"ranked":[170],"first":[171],"terms":[173],"F-measure":[175],"area":[178],"under":[179],"ROC":[181],"curve":[182],"given":[183]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}