{"id":"https://openalex.org/W1964853029","doi":"https://doi.org/10.1145/2536764.2536773","title":"Saliency-maximized audio visualization and efficient audio-visual browsing for faster-than-real-time human acoustic event detection","display_name":"Saliency-maximized audio visualization and efficient audio-visual browsing for faster-than-real-time human acoustic event detection","publication_year":2013,"publication_date":"2013-10-01","ids":{"openalex":"https://openalex.org/W1964853029","doi":"https://doi.org/10.1145/2536764.2536773","mag":"1964853029"},"language":"en","primary_location":{"id":"doi:10.1145/2536764.2536773","doi":"https://doi.org/10.1145/2536764.2536773","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2536764.2536773","pdf_url":null,"source":{"id":"https://openalex.org/S32453091","display_name":"ACM Transactions on Applied Perception","issn_l":"1544-3558","issn":["1544-3558","1544-3965"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","ccf-b","cwts-core","dongbi-b","jufo-1","norway-1","poland-70","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Applied Perception","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"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/A5102004603","display_name":"Kai-Hsiang Lin","orcid":"https://orcid.org/0000-0002-1214-8518","observed_orcids":["https://orcid.org/0000-0002-1214-8518"]},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kai-Hsiang Lin","raw_affiliation_strings":["University of Illinois at Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110376025","display_name":"Xiaodan Zhuang","orcid":"https://orcid.org/0009-0004-5481-8630","observed_orcids":["https://orcid.org/0009-0004-5481-8630"]},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaodan Zhuang","raw_affiliation_strings":["University of Illinois at Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077548822","display_name":"Camille M. A. Goudeseune","orcid":"https://orcid.org/0000-0003-3530-8577","observed_orcids":["https://orcid.org/0000-0003-3530-8577"]},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Camille Goudeseune","raw_affiliation_strings":["University of Illinois at Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112611802","display_name":"Sarah King","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sarah King","raw_affiliation_strings":["University of Illinois at Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004778663","display_name":"Mark Hasegawa\u2010Johnson","orcid":"https://orcid.org/0000-0002-5631-2893","observed_orcids":["https://orcid.org/0000-0002-5631-2893"]},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Hasegawa-Johnson","raw_affiliation_strings":["University of Illinois at Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101457342","display_name":"Thomas S. Huang","orcid":"https://orcid.org/0000-0001-8474-5859","observed_orcids":["https://orcid.org/0000-0001-8474-5859"]},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thomas S. Huang","raw_affiliation_strings":["University of Illinois at Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":0.3624,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.65684647,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":93},"biblio":{"volume":"10","issue":"4","first_page":"1","last_page":"16"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.8720999956130981,"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":0.8720999956130981,"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/T10799","display_name":"Data Visualization and Analytics","score":0.09000000357627869,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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":0.011900000274181366,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/sound-visualization","display_name":"sound visualization","score":0.7730000019073486},{"id":"https://openalex.org/keywords/sound-event-detection","display_name":"sound event detection","score":0.8500000238418579},{"id":"https://openalex.org/keywords/spectrogram","display_name":"spectrogram","score":0.4659999907016754},{"id":"https://openalex.org/keywords/mutual-information","display_name":"mutual information","score":0.7609999775886536},{"id":"https://openalex.org/keywords/sound-archives","display_name":"sound archives","score":0.6370000243186951}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.9040288329124451},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7704952955245972},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.7568914294242859},{"id":"https://openalex.org/C124913957","wikidata":"https://www.wikidata.org/wiki/Q1232548","display_name":"Zoom","level":3,"score":0.626537561416626},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5593137741088867},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5489344596862793},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.543424129486084},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5265738368034363},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.5214278697967529},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.45759469270706177},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4345918297767639},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4307391047477722},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.41363999247550964},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4051687717437744},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35897934436798096},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.13463875651359558},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.0991988480091095},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C15336307","wikidata":"https://www.wikidata.org/wiki/Q1766051","display_name":"Lens (geology)","level":2,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"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/C78762247","wikidata":"https://www.wikidata.org/wiki/Q1273174","display_name":"Petroleum engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/2536764.2536773","doi":"https://doi.org/10.1145/2536764.2536773","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2536764.2536773","pdf_url":null,"source":{"id":"https://openalex.org/S32453091","display_name":"ACM Transactions on Applied Perception","issn_l":"1544-3558","issn":["1544-3558","1544-3965"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","ccf-b","cwts-core","dongbi-b","jufo-1","norway-1","poland-70","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Applied Perception","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.303.2420","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.303.2420","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.isle.uiuc.edu/%7Esborys/Saliency_audio_visualization-Lin.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.357.2193","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.357.2193","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.isle.illinois.edu/pubs/2013/lin13tap.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G471084420","display_name":null,"funder_award_id":"807329","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W56793145","https://openalex.org/W147723833","https://openalex.org/W1481873330","https://openalex.org/W1557496348","https://openalex.org/W1627054999","https://openalex.org/W1645564793","https://openalex.org/W1902027874","https://openalex.org/W1918020955","https://openalex.org/W1969581814","https://openalex.org/W1984314602","https://openalex.org/W1997062464","https://openalex.org/W2017288758","https://openalex.org/W2022203357","https://openalex.org/W2041404167","https://openalex.org/W2046863527","https://openalex.org/W2068419217","https://openalex.org/W2083751884","https://openalex.org/W2084279352","https://openalex.org/W2099111195","https://openalex.org/W2104298926","https://openalex.org/W2106582496","https://openalex.org/W2110755006","https://openalex.org/W2117613041","https://openalex.org/W2128272608","https://openalex.org/W2133059825","https://openalex.org/W2134917048","https://openalex.org/W2143603136","https://openalex.org/W2153937809","https://openalex.org/W2164084182","https://openalex.org/W2165343926","https://openalex.org/W2170161511","https://openalex.org/W2329114374","https://openalex.org/W2478708596","https://openalex.org/W2579555219","https://openalex.org/W2798189423","https://openalex.org/W3140400178","https://openalex.org/W3143835353","https://openalex.org/W4245942730","https://openalex.org/W4250059488"],"related_works":["https://openalex.org/W2117613041","https://openalex.org/W3141354337","https://openalex.org/W1589138511","https://openalex.org/W2780718603","https://openalex.org/W1011837647","https://openalex.org/W1913602411","https://openalex.org/W3032894527","https://openalex.org/W2883943760","https://openalex.org/W7204772515","https://openalex.org/W50920816"],"abstract_inverted_index":{"Browsing":[0],"large":[1],"audio":[2,26,36,83],"archives":[3],"is":[4],"challenging":[5],"because":[6],"of":[7,10,24,53,77,125],"the":[8,25,42,56,118,122],"limitations":[9],"human":[11],"audition":[12],"and":[13,50,68,90,128],"attention.":[14],"However,":[15],"this":[16],"task":[17],"becomes":[18],"easier":[19],"with":[20,70],"a":[21,30,96],"suitable":[22],"visualization":[23],"signal,":[27],"such":[28,64],"as":[29],"spectrogram":[31,49],"transformed":[32],"to":[33,136],"make":[34],"unusual":[35],"events":[37,80],"salient.":[38],"This":[39],"transformation":[40],"maximizes":[41],"mutual":[43,119],"information":[44,120],"between":[45,121],"an":[46,51],"isolated":[47],"event's":[48],"estimate":[52],"how":[54],"salient":[55],"event":[57,99],"appears":[58],"in":[59,81,95],"its":[60],"surrounding":[61],"context.":[62],"When":[63],"spectrograms":[65,110],"are":[66],"computed":[67],"displayed":[69],"fluid":[71],"zooming":[72],"over":[73],"many":[74],"temporal":[75],"orders":[76],"magnitude,":[78],"sparse":[79],"long":[82],"recordings":[84],"can":[85],"be":[86],"detected":[87],"more":[88,91,131],"quickly":[89],"easily.":[92],"In":[93],"particular,":[94],"1/10-real-time":[97],"acoustic":[98],"detection":[100],"task,":[101],"subjects":[102],"who":[103],"were":[104],"shown":[105],"saliency-maximized":[106],"rather":[107],"than":[108,132],"conventional":[109],"performed":[111],"significantly":[112],"better.":[113],"Saliency":[114],"maximization":[115],"also":[116],"improves":[117],"ground":[123],"truth":[124],"nonbackground":[126],"sounds":[127],"visual":[129],"saliency,":[130],"other":[133],"common":[134],"enhancements":[135],"visualization.":[137]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2016-06-24T00:00:00"}
