{"id":"https://openalex.org/W2102381657","doi":"https://doi.org/10.1109/aspaa.2011.6082331","title":"Spectral vs. spectro-temporal features for acoustic event detection","display_name":"Spectral vs. spectro-temporal features for acoustic event detection","publication_year":2011,"publication_date":"2011-10-01","ids":{"openalex":"https://openalex.org/W2102381657","doi":"https://doi.org/10.1109/aspaa.2011.6082331","mag":"2102381657"},"language":"en","primary_location":{"id":"doi:10.1109/aspaa.2011.6082331","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aspaa.2011.6082331","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","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/d8g450mq","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":true,"raw_author_name":"Courtenay V. Cotton","raw_affiliation_strings":["LabROSA, Department of Electrical Engineering, Columbia University, New York, NY, USA","LabROSA, Dept. of Electrical Engineering, Columbia University, 1300 S. W. Mudd, 500 West 120th Street, New York, 10027, USA"],"affiliations":[{"raw_affiliation_string":"LabROSA, Department of Electrical Engineering, Columbia University, New York, NY, USA","institution_ids":["https://openalex.org/I78577930"]},{"raw_affiliation_string":"LabROSA, Dept. of Electrical Engineering, Columbia University, 1300 S. W. Mudd, 500 West 120th Street, New York, 10027, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","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":["LabROSA, Department of Electrical Engineering, Columbia University, New York, NY, USA","LabROSA, Dept. of Electrical Engineering, Columbia University, 1300 S. W. Mudd, 500 West 120th Street, New York, 10027, USA"],"affiliations":[{"raw_affiliation_string":"LabROSA, Department of Electrical Engineering, Columbia University, New York, NY, USA","institution_ids":["https://openalex.org/I78577930"]},{"raw_affiliation_string":"LabROSA, Dept. of Electrical Engineering, Columbia University, 1300 S. W. Mudd, 500 West 120th Street, New York, 10027, USA","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5076254512"],"corresponding_institution_ids":["https://openalex.org/I78577930"],"apc_list":null,"apc_paid":null,"fwci":6.5359,"has_fulltext":false,"cited_by_count":137,"citation_normalized_percentile":{"value":0.97378057,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"69","last_page":"72"},"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":0.9991999864578247,"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":0.996999979019165,"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/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.8139961957931519},{"id":"https://openalex.org/keywords/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.8103985786437988},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7604502439498901},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.6619457006454468},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6126206517219543},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.581366240978241},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5766856074333191},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5249944925308228},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5016689300537109},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.48303231596946716},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4388408660888672},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.4300566613674164},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4278542399406433},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.34917354583740234}],"concepts":[{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.8139961957931519},{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.8103985786437988},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7604502439498901},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.6619457006454468},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6126206517219543},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.581366240978241},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5766856074333191},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5249944925308228},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5016689300537109},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.48303231596946716},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4388408660888672},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.4300566613674164},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4278542399406433},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.34917354583740234},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/aspaa.2011.6082331","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aspaa.2011.6082331","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},{"id":"pmh:oai:academiccommons.columbia.edu:10.7916/D8G450MQ","is_oa":false,"landing_page_url":"https://doi.org/10.7916/D8G450MQ","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/d8g450mq","is_oa":true,"landing_page_url":"https://doi.org/10.7916/d8g450mq","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/d8g450mq","is_oa":true,"landing_page_url":"https://doi.org/10.7916/d8g450mq","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1622490909","https://openalex.org/W1902027874","https://openalex.org/W2029165218","https://openalex.org/W2104298926","https://openalex.org/W2124149378","https://openalex.org/W2150040608","https://openalex.org/W2545232173","https://openalex.org/W4387533596"],"related_works":["https://openalex.org/W2127243424","https://openalex.org/W4390394189","https://openalex.org/W2037504162","https://openalex.org/W2539013788","https://openalex.org/W2792706544","https://openalex.org/W1568451138","https://openalex.org/W2156699640","https://openalex.org/W2045265907","https://openalex.org/W2972997031","https://openalex.org/W2075222291"],"abstract_inverted_index":{"Automatic":[0],"detection":[1,107],"of":[2,5,68,78,100,112,115,147,158],"different":[3],"types":[4],"acoustic":[6,48,117],"events":[7,49],"is":[8,62,72,141],"an":[9,42],"interesting":[10],"problem":[11,19],"in":[12,144],"soundtrack":[13],"processing.":[14],"Typical":[15],"approaches":[16],"to":[17,24,34,44,74,91],"the":[18,26,85,88,98,138,145,151,159],"use":[20],"short-term":[21,128],"spectral":[22],"features":[23,96],"describe":[25,84],"audio":[27],"signal,":[28],"with":[29,87,123],"additional":[30],"modeling":[31,47],"on":[32,108],"top":[33],"take":[35],"temporal":[36,53],"context":[37],"into":[38],"account.":[39],"We":[40,94,119,135],"propose":[41],"approach":[43,122],"detecting":[45],"and":[46,104,154],"that":[50,82,137,155],"directly":[51],"describes":[52],"context,":[54],"using":[55,126],"convolutive":[56],"non-negative":[57],"matrix":[58],"factorization":[59],"(NMF).":[60],"NMF":[61],"useful":[63],"for":[64],"finding":[65],"parts-based":[66],"decompositions":[67],"data;":[69],"here":[70],"it":[71],"used":[73],"discover":[75],"a":[76,109,124,156],"set":[77],"spectro-temporal":[79],"patch":[80,102],"bases":[81],"best":[83],"data,":[86],"patches":[89],"corresponding":[90],"event-like":[92],"structures.":[93],"derive":[95],"from":[97],"activations":[99],"these":[101],"bases,":[103],"perform":[105],"event":[106],"database":[110],"consisting":[111],"16":[113],"classes":[114],"meeting-room":[116],"events.":[118],"compare":[120],"our":[121],"baseline":[125],"standard":[127],"mel":[129],"frequency":[130],"cepstal":[131],"coefficient":[132],"(MFCC)":[133],"features.":[134],"demonstrate":[136],"event-based":[139],"system":[140],"more":[142],"robust":[143],"presence":[146],"added":[148],"noise":[149],"than":[150,165],"MFCC-based":[152],"system,":[153],"combination":[157],"two":[160],"systems":[161],"performs":[162],"even":[163],"better":[164],"either":[166],"individually.":[167]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":15},{"year":2018,"cited_by_count":16},{"year":2017,"cited_by_count":18},{"year":2016,"cited_by_count":10},{"year":2015,"cited_by_count":10},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":9},{"year":2012,"cited_by_count":3}],"updated_date":"2026-03-08T08:50:53.379069","created_date":"2025-10-10T00:00:00"}