{"id":"https://openalex.org/W2780718603","doi":"https://doi.org/10.1109/icassp.2018.8462062","title":"Eventness: Object Detection on Spectrograms for Temporal Localization of Audio Events","display_name":"Eventness: Object Detection on Spectrograms for Temporal Localization of Audio Events","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2780718603","doi":"https://doi.org/10.1109/icassp.2018.8462062","mag":"2780718603"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462062","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462062","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1712.09668","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059182099","display_name":"Phuong Thao Pham","orcid":"https://orcid.org/0000-0002-6205-1298"},"institutions":[{"id":"https://openalex.org/I50357001","display_name":"Universidad Carlos III de Madrid","ror":"https://ror.org/03ths8210","country_code":"ES","type":"education","lineage":["https://openalex.org/I50357001"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Phuong Pham","raw_affiliation_strings":["Power Electronics System Group, Universidad Carlos III de Madrid, Madrid, Spain"],"affiliations":[{"raw_affiliation_string":"Power Electronics System Group, Universidad Carlos III de Madrid, Madrid, Spain","institution_ids":["https://openalex.org/I50357001"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100648014","display_name":"Juncheng Li","orcid":"https://orcid.org/0000-0001-7314-6754"},"institutions":[{"id":"https://openalex.org/I50357001","display_name":"Universidad Carlos III de Madrid","ror":"https://ror.org/03ths8210","country_code":"ES","type":"education","lineage":["https://openalex.org/I50357001"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Juncheng Li","raw_affiliation_strings":["Power Electronics System Group, Universidad Carlos III de Madrid, Madrid, Spain"],"affiliations":[{"raw_affiliation_string":"Power Electronics System Group, Universidad Carlos III de Madrid, Madrid, Spain","institution_ids":["https://openalex.org/I50357001"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072368204","display_name":"Joseph Szurley","orcid":null},"institutions":[{"id":"https://openalex.org/I50357001","display_name":"Universidad Carlos III de Madrid","ror":"https://ror.org/03ths8210","country_code":"ES","type":"education","lineage":["https://openalex.org/I50357001"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Joseph Szurley","raw_affiliation_strings":["Power Electronics System Group, Universidad Carlos III de Madrid, Madrid, Spain"],"affiliations":[{"raw_affiliation_string":"Power Electronics System Group, Universidad Carlos III de Madrid, Madrid, Spain","institution_ids":["https://openalex.org/I50357001"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110454109","display_name":"Samarjit Das","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Samarjit Das","raw_affiliation_strings":["Schaltbau Sepsa, Madrid, Spain","[Schaltbau Sepsa, Madrid, Spain]"],"affiliations":[{"raw_affiliation_string":"Schaltbau Sepsa, Madrid, Spain","institution_ids":[]},{"raw_affiliation_string":"[Schaltbau Sepsa, Madrid, Spain]","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5059182099"],"corresponding_institution_ids":["https://openalex.org/I50357001"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00698844,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2491","last_page":"2495"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9983999729156494,"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/T10788","display_name":"Neuroscience and Music Perception","score":0.9812999963760376,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.8733350038528442},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7598775029182434},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6719179153442383},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.635439395904541},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6086674332618713},{"id":"https://openalex.org/keywords/clutter","display_name":"Clutter","score":0.5483768582344055},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5383672714233398},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4754768908023834},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.44599440693855286},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.42650774121284485},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4224797487258911},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40055447816848755},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4003939628601074},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.08157175779342651}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8733350038528442},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7598775029182434},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6719179153442383},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.635439395904541},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6086674332618713},{"id":"https://openalex.org/C132094186","wikidata":"https://www.wikidata.org/wiki/Q641585","display_name":"Clutter","level":3,"score":0.5483768582344055},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5383672714233398},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4754768908023834},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.44599440693855286},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.42650774121284485},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4224797487258911},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40055447816848755},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4003939628601074},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.08157175779342651},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2018.8462062","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462062","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1712.09668","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1712.09668","pdf_url":"https://arxiv.org/pdf/1712.09668","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"mag:2780718603","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1712.09668","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1712.09668","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1712.09668","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1712.09668","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1712.09668","pdf_url":"https://arxiv.org/pdf/1712.09668","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2780718603.pdf"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W603908379","https://openalex.org/W2038484192","https://openalex.org/W2065529590","https://openalex.org/W2077159900","https://openalex.org/W2090431713","https://openalex.org/W2102605133","https://openalex.org/W2566935005","https://openalex.org/W2593116425","https://openalex.org/W2951548327","https://openalex.org/W2953106684","https://openalex.org/W2963543871","https://openalex.org/W6618372016","https://openalex.org/W6620707391","https://openalex.org/W6628973269","https://openalex.org/W6631782140","https://openalex.org/W6632323398","https://openalex.org/W6635419406","https://openalex.org/W6636898527","https://openalex.org/W6643326691","https://openalex.org/W6660313906","https://openalex.org/W6669989999","https://openalex.org/W6673695152","https://openalex.org/W6675026286","https://openalex.org/W6734260513","https://openalex.org/W6734536791","https://openalex.org/W6747331233"],"related_works":["https://openalex.org/W3150049814","https://openalex.org/W1940377967","https://openalex.org/W3202586499","https://openalex.org/W3154852953","https://openalex.org/W1975143133","https://openalex.org/W3145267644","https://openalex.org/W2132033982","https://openalex.org/W3089377493","https://openalex.org/W2074321961","https://openalex.org/W2992822461","https://openalex.org/W2052487339","https://openalex.org/W3007977279","https://openalex.org/W2981895973","https://openalex.org/W3008500013","https://openalex.org/W3153016338","https://openalex.org/W179310991","https://openalex.org/W1476183714","https://openalex.org/W3042057498","https://openalex.org/W2418426001","https://openalex.org/W2150692043"],"abstract_inverted_index":{"In":[0],"this":[1,80],"paper,":[2],"we":[3,85,149],"introduce":[4],"the":[5,32,68,87,120,162],"concept":[6,34],"of":[7,19,89,156,170],"Eventness":[8],"for":[9],"audio":[10,37,94,121,163,171],"event":[11,122,172],"detection,":[12],"which":[13],"can,":[14],"in":[15,51,64,83,108],"part,":[16],"be":[17,58,159],"thought":[18],"as":[20,41,96],"an":[21,97],"analogue":[22],"to":[23,61,118,161],"Objectness":[24],"from":[25],"computer":[26],"vision.":[27],"The":[28,129],"key":[29,81],"observation":[30,82],"behind":[31],"eventness":[33,157],"is":[35,140],"that":[36,70,151],"events":[38,95],"reveal":[39],"themselves":[40],"2-dimensional":[42],"time-frequency":[43,54],"patterns":[44,55],"with":[45,135],"specific":[46],"textures":[47],"and":[48,72,106,139],"geometric":[49],"structures":[50],"spectrograms.":[52,109],"These":[53],"can":[56],"then":[57],"viewed":[59],"analogously":[60],"objects":[62],"occurring":[63],"natural":[65],"images":[66],"(with":[67],"exception":[69],"scaling":[71],"rotation":[73],"invariance":[74],"properties":[75],"do":[76],"not":[77],"apply).":[78],"With":[79],"mind,":[84],"pose":[86],"problem":[88,102],"detecting":[90],"monophonic":[91],"or":[92],"polyphonic":[93],"equivalent":[98],"visual":[99,114],"object(s)":[100],"detection":[101,116,123],"under":[103],"partial":[104],"occlusion":[105],"clutter":[107],"We":[110],"adapt":[111],"a":[112,136],"state-of-the-art":[113,137],"object":[115],"model":[117,155],"evaluate":[119],"task":[124],"on":[125,143],"publicly":[126],"available":[127],"datasets.":[128],"proposed":[130,153],"network":[131],"has":[132],"comparable":[133],"results":[134],"baseline":[138],"more":[141],"robust":[142],"minority":[144],"events.":[145],"Provided":[146],"large-scale":[147],"datasets,":[148],"hope":[150],"our":[152],"conceptual":[154],"will":[158],"beneficial":[160],"signal":[164],"processing":[165],"community":[166],"towards":[167],"improving":[168],"performance":[169],"detection.":[173]},"counts_by_year":[],"updated_date":"2026-03-11T14:59:36.786465","created_date":"2025-10-10T00:00:00"}