{"id":"https://openalex.org/W2097508275","doi":"https://doi.org/10.1109/icme.2014.6890234","title":"Improved audio features for large-scale multimedia event detection","display_name":"Improved audio features for large-scale multimedia event detection","publication_year":2014,"publication_date":"2014-07-01","ids":{"openalex":"https://openalex.org/W2097508275","doi":"https://doi.org/10.1109/icme.2014.6890234","mag":"2097508275"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2014.6890234","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2014.6890234","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://figshare.com/articles/journal_contribution/Improved_audio_features_for_large-scale_multimedia_event_detection/6473405","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085262529","display_name":"Florian Metze","orcid":"https://orcid.org/0000-0002-6663-8600"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Florian Metze","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, U.S.A","[Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, U.S.A]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, U.S.A","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"[Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, U.S.A]","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086192353","display_name":"Shourabh Rawat","orcid":"https://orcid.org/0009-0000-0160-3741"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shourabh Rawat","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, U.S.A","[Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, U.S.A]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, U.S.A","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"[Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, U.S.A]","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101401275","display_name":"Yipei Wang","orcid":"https://orcid.org/0000-0002-9589-7177"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yipei Wang","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, U.S.A","[Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, U.S.A]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, U.S.A","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"[Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, U.S.A]","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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":0.9998000264167786,"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":0.9994999766349792,"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":0.869316816329956},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.7577309608459473},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.7065727710723877},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6826945543289185},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.6141424775123596},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5548025965690613},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5407277941703796},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5169546008110046},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5101602673530579},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.46091750264167786},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.45681723952293396},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.44471079111099243},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4164174497127533},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.4104878604412079},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3745534420013428},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.2785710096359253},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.20962747931480408}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.869316816329956},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.7577309608459473},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.7065727710723877},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6826945543289185},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.6141424775123596},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5548025965690613},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5407277941703796},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5169546008110046},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5101602673530579},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.46091750264167786},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.45681723952293396},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.44471079111099243},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4164174497127533},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.4104878604412079},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3745534420013428},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.2785710096359253},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.20962747931480408},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/icme.2014.6890234","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2014.6890234","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.cmu.edu:lti-1074","is_oa":false,"landing_page_url":"http://repository.cmu.edu/lti/66","pdf_url":null,"source":{"id":"https://openalex.org/S4306400668","display_name":"Research Showcase @ Carnegie Mellon University (Carnegie Mellon University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I74973139","host_organization_name":"Carnegie Mellon University","host_organization_lineage":["https://openalex.org/I74973139"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Language Technologies Institute","raw_type":"text"},{"id":"pmh:doi:10.1184/r1/6473405","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal contribution"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.830.6678","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.830.6678","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://repository.cmu.edu/cgi/viewcontent.cgi?article%3D1074%26context%3Dlti","raw_type":"text"},{"id":"pmh:oai:figshare.com:article/6473405","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/Improved_audio_features_for_large-scale_multimedia_event_detection/6473405","pdf_url":null,"source":{"id":"https://openalex.org/S4306402621","display_name":"INDIGO (University of Illinois at Chicago)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I39422238","host_organization_name":"University of Illinois Chicago","host_organization_lineage":["https://openalex.org/I39422238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"doi:10.1184/r1/6473405.v1","is_oa":true,"landing_page_url":"https://doi.org/10.1184/r1/6473405.v1","pdf_url":null,"source":{"id":"https://openalex.org/S7407050927","display_name":"KiltHub Repository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"JournalArticle"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/6473405","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/Improved_audio_features_for_large-scale_multimedia_event_detection/6473405","pdf_url":null,"source":{"id":"https://openalex.org/S4306402621","display_name":"INDIGO (University of Illinois at Chicago)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I39422238","host_organization_name":"University of Illinois Chicago","host_organization_lineage":["https://openalex.org/I39422238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4300000071525574}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306116","display_name":"U.S. Department of the Interior","ror":"https://ror.org/03v0pmy70"},{"id":"https://openalex.org/F4320333452","display_name":"Interior Business Center","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1460854341","https://openalex.org/W1535031652","https://openalex.org/W1559922967","https://openalex.org/W1600745603","https://openalex.org/W1970088388","https://openalex.org/W1998139235","https://openalex.org/W2004906691","https://openalex.org/W2065784292","https://openalex.org/W2085662862","https://openalex.org/W2103869314","https://openalex.org/W2134756243","https://openalex.org/W2144211451","https://openalex.org/W2152175008","https://openalex.org/W2159948109","https://openalex.org/W2160815625","https://openalex.org/W2164311876","https://openalex.org/W2186804261","https://openalex.org/W2252254117","https://openalex.org/W2401143228","https://openalex.org/W2402668451","https://openalex.org/W2408491073","https://openalex.org/W6628533439","https://openalex.org/W6633383461","https://openalex.org/W6683644788","https://openalex.org/W6684362472","https://openalex.org/W6686878303","https://openalex.org/W6691726237","https://openalex.org/W6712982002","https://openalex.org/W6713038350","https://openalex.org/W6714426239"],"related_works":["https://openalex.org/W2254811285","https://openalex.org/W4210770212","https://openalex.org/W2291847203","https://openalex.org/W2313168606","https://openalex.org/W2951391129","https://openalex.org/W3137509671","https://openalex.org/W1901836159","https://openalex.org/W4205555939","https://openalex.org/W2107940618","https://openalex.org/W2097508275"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,127],"present":[4],"recent":[5],"experiments":[6],"on":[7,88],"using":[8,35,97],"Artificial":[9],"Neural":[10],"Networks":[11],"(ANNs),":[12],"a":[13,46,51,65,73],"new":[14],"\u201cdelayed\u201d":[15],"approach":[16],"to":[17,44,159],"speech":[18],"vs.":[19],"non-speech":[20],"segmentation,":[21],"and":[22,71,80,85,152],"extraction":[23],"of":[24,48,68,75,142,149],"large-scale":[25],"pooling":[26],"feature":[27],"(LSPF)":[28],"for":[29],"detecting":[30],"\u201cevents\u201d":[31],"within":[32],"consumer":[33],"videos,":[34],"the":[36,69,89,99,110,118],"audio":[37],"channel":[38],"only.":[39],"A":[40],"\u201cevent\u201d":[41],"is":[42,62,121],"defined":[43],"be":[45,55],"sequence":[47],"observations":[49],"in":[50,113],"video,":[52],"that":[53,122,129],"can":[54],"directly":[56],"observed":[57],"or":[58],"inferred.":[59],"Ground":[60],"truth":[61],"given":[63],"by":[64,72],"semantic":[66],"description":[67],"event,":[70],"number":[74],"example":[76],"videos.":[77],"We":[78],"describe":[79],"compare":[81],"several":[82],"algorithmic":[83],"approaches,":[84],"report":[86],"results":[87,112],"2013":[90],"TRECVID":[91],"Multimedia":[92],"Event":[93],"Detection":[94],"(MED)":[95],"task,":[96],"arguably":[98],"largest":[100],"such":[101],"research":[102],"set":[103],"currently":[104],"available.":[105],"The":[106],"presented":[107],"system":[108,161],"achieved":[109],"best":[111],"most":[114],"audio-only":[115],"conditions.":[116],"While":[117],"overall":[119,160],"finding":[120],"MFCC":[123],"features":[124,135],"perform":[125],"best,":[126],"find":[128],"ANN":[130],"as":[131,133],"well":[132],"LSP":[134],"provide":[136],"complementary":[137],"information":[138],"at":[139],"various":[140],"levels":[141],"temporal":[143],"resolution.":[144],"This":[145],"paper":[146],"provides":[147],"analysis":[148],"both":[150],"low-level":[151],"high-level":[153],"features,":[154],"investigating":[155],"their":[156],"relative":[157],"contributions":[158],"performance.":[162]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
