{"id":"https://openalex.org/W2137441914","doi":"https://doi.org/10.1109/icassp.2010.5495915","title":"Detecting local semantic concepts in environmental sounds using Markov model based clustering","display_name":"Detecting local semantic concepts in environmental sounds using Markov model based clustering","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W2137441914","doi":"https://doi.org/10.1109/icassp.2010.5495915","mag":"2137441914"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2010.5495915","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495915","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","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/d89s21d9","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052238175","display_name":"Keansub Lee","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":"Keansub Lee","raw_affiliation_strings":["LabROSA, Dept. of Elec. Eng., Columbia University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LabROSA, Dept. of Elec. Eng., 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":["LabROSA, Dept. of Elec. Eng., Columbia University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LabROSA, Dept. of Elec. Eng., 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/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":"Alexander C. Loui","raw_affiliation_strings":["LabROSA, Dept. of Elec. Eng., Columbia University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LabROSA, Dept. of Elec. Eng., Columbia University, USA","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.725,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.93926302,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2278","last_page":"2281"},"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":0.9969000220298767,"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":0.9900000095367432,"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/computer-science","display_name":"Computer science","score":0.8055352568626404},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7674339413642883},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6569809317588806},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.6324342489242554},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5885873436927795},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5865471363067627},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5782390832901001},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46124735474586487},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.36048245429992676},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3443170487880707}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8055352568626404},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7674339413642883},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6569809317588806},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.6324342489242554},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5885873436927795},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5865471363067627},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5782390832901001},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46124735474586487},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36048245429992676},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3443170487880707},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/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.2010.5495915","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495915","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.157.6291","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.157.6291","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://labrosa.ee.columbia.edu/~dpwe/pubs/LeeEL10-localconcepts.pdf","raw_type":"text"},{"id":"pmh:oai:academiccommons.columbia.edu:10.7916/D89S21D9","is_oa":false,"landing_page_url":"https://doi.org/10.7916/D89S21D9","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/d89s21d9","is_oa":true,"landing_page_url":"https://doi.org/10.7916/d89s21d9","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/d89s21d9","is_oa":true,"landing_page_url":"https://doi.org/10.7916/d89s21d9","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":[{"display_name":"Life in Land","id":"https://metadata.un.org/sdg/15","score":0.699999988079071}],"awards":[],"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":6,"referenced_works":["https://openalex.org/W2036931824","https://openalex.org/W2077072595","https://openalex.org/W2105438720","https://openalex.org/W2120995095","https://openalex.org/W2154318594","https://openalex.org/W6683033130"],"related_works":["https://openalex.org/W2053269318","https://openalex.org/W2364370872","https://openalex.org/W2025614924","https://openalex.org/W2294335174","https://openalex.org/W2097963413","https://openalex.org/W3145575561","https://openalex.org/W2001275470","https://openalex.org/W2073996508","https://openalex.org/W1591475660","https://openalex.org/W2157423375"],"abstract_inverted_index":{"Detecting":[0],"the":[1,77,84],"time":[2,85],"of":[3,5,47,63,83,90],"occurrence":[4],"an":[6],"acoustic":[7],"event":[8],"(for":[9],"instance,":[10],"a":[11,15,35,61,88],"cheer)":[12],"embedded":[13],"in":[14,29,67],"longer":[16],"soundtrack":[17],"is":[18,114],"useful":[19],"and":[20,27,43,57,110],"important":[21],"for":[22,120],"applications":[23],"such":[24],"as":[25],"search":[26],"retrieval":[28],"consumer":[30,123],"video":[31],"archives.":[32],"We":[33],"present":[34],"Markov-model":[36],"based":[37,106],"clustering":[38,104],"algorithm":[39],"able":[40],"to":[41,59],"identify":[42],"segment":[44],"consistent":[45],"sets":[46],"temporal":[48],"frames":[49,65],"into":[50],"regions":[51],"associated":[52],"with":[53],"different":[54],"ground-truth":[55],"labels,":[56,109],"simultaneously":[58],"exclude":[60],"set":[62],"uninformative":[64],"shared":[66],"common":[68],"from":[69],"all":[70],"clips.":[71],"The":[72],"labels":[73],"are":[74,99],"provided":[75],"at":[76],"clip":[78],"level,":[79],"so":[80],"this":[81,103],"refinement":[82],"axis":[86],"represents":[87],"variant":[89],"Multiple-Instance":[91],"Learning":[92],"(MIL).":[93],"Evaluation":[94],"shows":[95],"that":[96,111],"local":[97],"concepts":[98],"effectively":[100],"detected":[101],"by":[102],"technique":[105],"on":[107],"coarse-scale":[108],"detection":[112],"performance":[113],"significantly":[115],"better":[116],"than":[117],"existing":[118],"algorithms":[119],"classifying":[121],"real-world":[122],"recordings.":[124]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}