{"id":"https://openalex.org/W2150040608","doi":"https://doi.org/10.1109/icassp.2011.5946443","title":"Soundtrack classification by transient events","display_name":"Soundtrack classification by transient events","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2150040608","doi":"https://doi.org/10.1109/icassp.2011.5946443","mag":"2150040608"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5946443","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5946443","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.7916/d8v98jfc","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076254512","display_name":"Courtenay V. Cotton","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Courtenay V. Cotton","raw_affiliation_strings":["Laboratory ROSA, Department of Electrical Engineering, Columbia University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratory ROSA, Department of Electrical Engineering, Columbia University, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055458377","display_name":"Daniel P. W. Ellis","orcid":"https://orcid.org/0000-0002-5076-4311"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel P. W. Ellis","raw_affiliation_strings":["Laboratory ROSA, Department of Electrical Engineering, Columbia University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratory ROSA, Department of Electrical Engineering, Columbia University, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051767562","display_name":"Alexander C. Loui","orcid":"https://orcid.org/0000-0002-7427-1503"},"institutions":[{"id":"https://openalex.org/I4210094723","display_name":"Kodak (Japan)","ror":"https://ror.org/00tee0349","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210094723","https://openalex.org/I4210159451"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Alexander C. Loui","raw_affiliation_strings":["Kodak Research Laboratories, Eastman Kodak (Japan) Limited, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kodak Research Laboratories, Eastman Kodak (Japan) Limited, USA","institution_ids":["https://openalex.org/I4210094723"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.6814,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.95584213,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"473","last_page":"476"},"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":0.9979000091552734,"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":0.9876999855041504,"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/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.9085338115692139},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7620357275009155},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.6355001330375671},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.57737135887146},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5568248629570007},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5267139077186584},{"id":"https://openalex.org/keywords/transient","display_name":"Transient (computer programming)","score":0.5231469869613647},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5178287625312805},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.5110198259353638},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5060235857963562},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.42713695764541626},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.34566524624824524}],"concepts":[{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.9085338115692139},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7620357275009155},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6355001330375671},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.57737135887146},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5568248629570007},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5267139077186584},{"id":"https://openalex.org/C2780799671","wikidata":"https://www.wikidata.org/wiki/Q17087362","display_name":"Transient (computer programming)","level":2,"score":0.5231469869613647},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5178287625312805},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.5110198259353638},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5060235857963562},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42713695764541626},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.34566524624824524},{"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2011.5946443","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5946443","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.228.1524","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.228.1524","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ee.columbia.edu/%7Edpwe/pubs/CottonE11-transient.pdf","raw_type":"text"},{"id":"pmh:oai:academiccommons.columbia.edu:10.7916/D8V98JFC","is_oa":false,"landing_page_url":"https://doi.org/10.7916/D8V98JFC","pdf_url":null,"source":{"id":"https://openalex.org/S4306402601","display_name":"Columbia Academic Commons (Columbia University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I78577930","host_organization_name":"Columbia University","host_organization_lineage":["https://openalex.org/I78577930"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Articles"},{"id":"doi:10.7916/d8v98jfc","is_oa":true,"landing_page_url":"https://doi.org/10.7916/d8v98jfc","pdf_url":null,"source":{"id":"https://openalex.org/S4306402601","display_name":"Columbia Academic Commons (Columbia University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I78577930","host_organization_name":"Columbia University","host_organization_lineage":["https://openalex.org/I78577930"],"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-journal"}],"best_oa_location":{"id":"doi:10.7916/d8v98jfc","is_oa":true,"landing_page_url":"https://doi.org/10.7916/d8v98jfc","pdf_url":null,"source":{"id":"https://openalex.org/S4306402601","display_name":"Columbia Academic Commons (Columbia University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I78577930","host_organization_name":"Columbia University","host_organization_lineage":["https://openalex.org/I78577930"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2036931824","https://openalex.org/W2073295754","https://openalex.org/W2077072595","https://openalex.org/W2144037622","https://openalex.org/W2152909444","https://openalex.org/W6669543024"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W4385672897","https://openalex.org/W2373675101","https://openalex.org/W106160982","https://openalex.org/W2359140082","https://openalex.org/W2074132948","https://openalex.org/W4317383455","https://openalex.org/W2548511587"],"abstract_inverted_index":{"We":[0,68],"present":[1],"a":[2,73,104],"method":[3,71],"for":[4],"video":[5],"classification":[6],"based":[7,87],"on":[8,29,40,72,88],"information":[9],"in":[10,109],"the":[11,18,52,55,100],"soundtrack.":[12],"Unlike":[13],"previous":[14],"approaches":[15],"which":[16],"describe":[17],"audio":[19,41],"via":[20],"statistics":[21],"of":[22,54,76,107],"mel-frequency":[23],"cepstral":[24],"coefficient":[25],"(MFCC)":[26],"features":[27,49,90],"calculated":[28],"uniformly-spaced":[30],"frames,":[31],"we":[32],"investigate":[33],"an":[34,95],"approach":[35],"to":[36,44,94],"focusing":[37],"our":[38,70],"representation":[39],"transients":[42],"corresponding":[43],"sound-track":[45],"events.":[46],"These":[47],"event-related":[48],"can":[50],"reflect":[51],"\"foreground\"":[53],"soundtrack":[56],"and":[57,98],"capture":[58],"its":[59],"short-term":[60],"temporal":[61],"structure":[62],"better":[63],"than":[64],"conventional":[65],"frame-based":[66],"statistics.":[67],"evaluate":[69],"test":[74],"set":[75],"1873":[77],"YouTube":[78],"videos":[79],"labeled":[80],"with":[81],"25":[82],"semantic":[83],"concepts.":[84],"Retrieval":[85],"results":[86],"transient":[89],"alone":[91],"are":[92],"comparable":[93],"MFCC-based":[96],"system,":[97],"fusing":[99],"two":[101],"representations":[102],"achieves":[103],"relative":[105],"improvement":[106],"7.5%":[108],"mean":[110],"average":[111],"precision":[112],"(MAP).":[113]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":7}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}