{"id":"https://openalex.org/W2057592954","doi":"https://doi.org/10.1109/icassp.2013.6638340","title":"Extracting spoken and acoustic concepts for multimedia event detection","display_name":"Extracting spoken and acoustic concepts for multimedia event detection","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2057592954","doi":"https://doi.org/10.1109/icassp.2013.6638340","mag":"2057592954"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6638340","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6638340","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5058481276","display_name":"Julien van Hout","orcid":null},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Julien van Hout","raw_affiliation_strings":["Speech Technology and Research Laboratory, SRI International, Menlo Park, CA, USA","Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA"],"affiliations":[{"raw_affiliation_string":"Speech Technology and Research Laboratory, SRI International, Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152"]},{"raw_affiliation_string":"Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076998541","display_name":"Murat Akbacak","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Murat Akbacak","raw_affiliation_strings":["Microsoft, Sunnyvale, CA, USA","Microsoft, Sunnyvale, CA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Microsoft, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, Sunnyvale, CA, USA#TAB#","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013886109","display_name":"Diego Cast\u00e1n","orcid":null},"institutions":[{"id":"https://openalex.org/I255234318","display_name":"Universidad de Zaragoza","ror":"https://ror.org/012a91z28","country_code":"ES","type":"education","lineage":["https://openalex.org/I255234318"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Diego Castan","raw_affiliation_strings":["ViVoLab-I3A, University of Zaragoza, Zaragoza, Spain","ViVoLab I3A, University of Zaragoza, Zaragoza, Spain"],"affiliations":[{"raw_affiliation_string":"ViVoLab-I3A, University of Zaragoza, Zaragoza, Spain","institution_ids":["https://openalex.org/I255234318"]},{"raw_affiliation_string":"ViVoLab I3A, University of Zaragoza, Zaragoza, Spain","institution_ids":["https://openalex.org/I255234318"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026603897","display_name":"Eric Yeh","orcid":"https://orcid.org/0000-0001-8752-4429"},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric Yeh","raw_affiliation_strings":["Speech Technology and Research Laboratory, SRI International, Menlo Park, CA, USA","Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA"],"affiliations":[{"raw_affiliation_string":"Speech Technology and Research Laboratory, SRI International, Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152"]},{"raw_affiliation_string":"Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065053594","display_name":"Michelle Hewlett Sanchez","orcid":null},"institutions":[{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]},{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michelle Sanchez","raw_affiliation_strings":["Speech Technology and Research Laboratory, SRI International, Menlo Park, CA, USA","Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA"],"affiliations":[{"raw_affiliation_string":"Speech Technology and Research Laboratory, SRI International, Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152"]},{"raw_affiliation_string":"Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5058481276"],"corresponding_institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"],"apc_list":null,"apc_paid":null,"fwci":2.8729,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.91261567,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"19","issue":null,"first_page":"3657","last_page":"3661"},"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":0.9993000030517578,"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":0.9988999962806702,"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":0.815863847732544},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6822686195373535},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.6029456853866577},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.5622206330299377},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.537732720375061},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5270885825157166},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44195619225502014},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4157909154891968},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39727622270584106},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.38225314021110535},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3379708528518677}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.815863847732544},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6822686195373535},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.6029456853866577},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.5622206330299377},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.537732720375061},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5270885825157166},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44195619225502014},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4157909154891968},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39727622270584106},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.38225314021110535},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3379708528518677}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2013.6638340","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6638340","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6600000262260437,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306116","display_name":"U.S. Department of the Interior","ror":"https://ror.org/03v0pmy70"},{"id":"https://openalex.org/F4320332178","display_name":"National Institute of Standards and Technology","ror":"https://ror.org/05xpvk416"},{"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":18,"referenced_works":["https://openalex.org/W88081813","https://openalex.org/W150825499","https://openalex.org/W1600745603","https://openalex.org/W1753516808","https://openalex.org/W2004906691","https://openalex.org/W2098162425","https://openalex.org/W2117099982","https://openalex.org/W2120779048","https://openalex.org/W2128383159","https://openalex.org/W2141939040","https://openalex.org/W2182437395","https://openalex.org/W2282649501","https://openalex.org/W2394840413","https://openalex.org/W2401143228","https://openalex.org/W6603616073","https://openalex.org/W6606080022","https://openalex.org/W6678039958","https://openalex.org/W6686129731"],"related_works":["https://openalex.org/W2157598242","https://openalex.org/W3159882232","https://openalex.org/W4241650944","https://openalex.org/W2620660273","https://openalex.org/W4243125559","https://openalex.org/W1541790149","https://openalex.org/W2964829415","https://openalex.org/W2131711534","https://openalex.org/W642007152","https://openalex.org/W2341426843"],"abstract_inverted_index":{"Because":[0],"of":[1,4,21,120,139,196,204],"the":[2,19,63,88,116,140,166,178,201],"popularity":[3],"online":[5,22],"videos,":[6],"there":[7],"has":[8],"been":[9],"much":[10],"interest":[11],"in":[12,15,157,175],"recent":[13],"years":[14],"audio":[16,38,64],"processing":[17],"for":[18,44],"improvement":[20,156,192],"video":[23],"search.":[24],"In":[25],"this":[26],"paper,":[27],"we":[28,186],"explore":[29],"using":[30,115,150,182],"acoustic":[31],"concepts":[32,35,112,149,169],"and":[33,40,70,85],"spoken":[34,51,148,168],"extracted":[36,114],"via":[37],"segmentation/recognition":[39],"speech":[41,74],"recognition":[42],"respectively":[43],"Multimedia":[45],"Event":[46],"Detection":[47],"(MED).":[48],"To":[49],"extract":[50],"concepts,":[52],"a":[53,137,153,171],"segmenter":[54],"trained":[55,127],"on":[56,128,136],"annotated":[57],"data":[58],"from":[59,87,99],"user":[60],"videos":[61],"segments":[62,75],"into":[65],"three":[66],"classes:":[67],"speech,":[68],"music,":[69],"other":[71],"sounds.":[72],"The":[73],"are":[76,102,113,134],"passed":[77],"to":[78,106],"an":[79,107,188],"Automatic":[80],"Speech":[81],"Recognition":[82,124],"(ASR)":[83],"engine,":[84],"words":[86],"1-best":[89,162],"ASR":[90,100],"output,":[91],"as":[92,94,104],"well":[93],"posterior-weighted":[95],"word":[96],"counts":[97,119],"collected":[98],"lattices,":[101],"used":[103],"features":[105],"SVM":[108],"based":[109,163],"classifier.":[110],"Acoustic":[111,122],"3-gram":[117],"lattice":[118],"two":[121],"Concept":[123],"(ACR)":[125],"systems":[126],"7":[129,183],"broad":[130],"classes.":[131,184],"MED":[132,180],"results":[133],"reported":[135],"subset":[138],"NIST":[141],"2011":[142],"TRECVID":[143],"data.":[144],"We":[145],"find":[146],"that":[147],"lattices":[151],"yield":[152],"15%":[154],"relative":[155,173,190],"Average":[158],"Pmiss":[159],"(APM)":[160],"over":[161,177],"features.":[164],"Further,":[165],"proposed":[167],"gave":[170],"30%":[172],"gain":[174],"APM":[176,191],"ACR-based":[179],"system":[181],"Lastly,":[185],"obtain":[187],"8%":[189],"after":[193],"score-level":[194],"fusion":[195],"both":[197,205],"concept":[198],"types,":[199],"showing":[200],"effective":[202],"coupling":[203],"approaches.":[206]},"counts_by_year":[{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}