{"id":"https://openalex.org/W2037533030","doi":"https://doi.org/10.1145/2072298.2072022","title":"Environmental sound classification for scene recognition using local discriminant bases and HMM","display_name":"Environmental sound classification for scene recognition using local discriminant bases and HMM","publication_year":2011,"publication_date":"2011-11-28","ids":{"openalex":"https://openalex.org/W2037533030","doi":"https://doi.org/10.1145/2072298.2072022","mag":"2037533030"},"language":"en","primary_location":{"id":"doi:10.1145/2072298.2072022","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2072298.2072022","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th ACM international conference on Multimedia","raw_type":"proceedings-article"},"type":"article","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/A5006378862","display_name":"Feng Su","orcid":"https://orcid.org/0000-0002-8426-9634"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Feng Su","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100645665","display_name":"Li Yang","orcid":"https://orcid.org/0000-0002-1889-3113"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Yang","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061696740","display_name":"Tong L\u00fc","orcid":"https://orcid.org/0000-0002-7051-5347"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tong Lu","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077378861","display_name":"Gongyou Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gongyou Wang","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5006378862"],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":5.28113212,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.96213081,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1389","last_page":"1392"},"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":0.9976999759674072,"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/T11665","display_name":"Animal Vocal Communication and Behavior","score":0.9779999852180481,"subfield":{"id":"https://openalex.org/subfields/1309","display_name":"Developmental Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.820897102355957},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7622635364532471},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.576766848564148},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5750178098678589},{"id":"https://openalex.org/keywords/linear-discriminant-analysis","display_name":"Linear discriminant analysis","score":0.565062940120697},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5544101595878601},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5391066670417786},{"id":"https://openalex.org/keywords/auditory-scene-analysis","display_name":"Auditory scene analysis","score":0.5164515972137451},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.5110889077186584},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.4958377778530121},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.48905453085899353},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4886093735694885},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4561663269996643},{"id":"https://openalex.org/keywords/discriminant","display_name":"Discriminant","score":0.4186549186706543},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.2818397283554077},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.08260086178779602}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.820897102355957},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7622635364532471},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.576766848564148},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5750178098678589},{"id":"https://openalex.org/C69738355","wikidata":"https://www.wikidata.org/wiki/Q1228929","display_name":"Linear discriminant analysis","level":2,"score":0.565062940120697},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5544101595878601},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5391066670417786},{"id":"https://openalex.org/C38129911","wikidata":"https://www.wikidata.org/wiki/Q4820038","display_name":"Auditory scene analysis","level":3,"score":0.5164515972137451},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.5110889077186584},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.4958377778530121},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.48905453085899353},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4886093735694885},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4561663269996643},{"id":"https://openalex.org/C78397625","wikidata":"https://www.wikidata.org/wiki/Q192487","display_name":"Discriminant","level":2,"score":0.4186549186706543},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.2818397283554077},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.08260086178779602},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2072298.2072022","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2072298.2072022","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th ACM international conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7200000286102295,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2035071469","https://openalex.org/W2100813490","https://openalex.org/W2117647820","https://openalex.org/W2120599713","https://openalex.org/W2126109423","https://openalex.org/W2130640900","https://openalex.org/W2137343183","https://openalex.org/W2154221499","https://openalex.org/W2166706387"],"related_works":["https://openalex.org/W2350751952","https://openalex.org/W2362114017","https://openalex.org/W1999647744","https://openalex.org/W3147024994","https://openalex.org/W1978302214","https://openalex.org/W2374055396","https://openalex.org/W2063246903","https://openalex.org/W2021817983","https://openalex.org/W3021047493","https://openalex.org/W2371177901"],"abstract_inverted_index":{"Analysis":[0],"and":[1,14,19,30,41,75,114],"classification":[2],"of":[3,16,43,47,129],"auditory":[4,31,99,134],"scenes":[5],"or":[6,92],"contexts":[7],"play":[8],"important":[9],"roles":[10],"in":[11,101],"content-based":[12],"indexing":[13],"retrieval":[15],"multimedia":[17],"databases":[18],"context-aware":[20],"applications.":[21],"In":[22],"this":[23],"paper,":[24],"we":[25,86],"propose":[26,57],"an":[27],"environmental":[28,73],"sound":[29,95],"scene":[32,49,135],"recognition":[33,89],"scheme":[34],"that":[35,119],"focuses":[36],"on":[37,84],"efficient":[38],"feature":[39,81],"representation":[40],"classfication":[42],"the":[44,60,68,103,112,121,127,130],"unstructured":[45],"composition":[46],"a":[48],"(for":[50],"example,":[51],"restaurant,":[52],"street,":[53],"beach,":[54],"etc.).":[55],"We":[56],"to":[58,66,110],"use":[59,77],"local":[61],"discriminant":[62],"bases":[63],"(LDB)":[64],"technique":[65],"identify":[67],"discriminatory":[69],"time-frequency":[70],"subspace":[71],"for":[72,79,98,133],"sounds":[74],"then":[76],"it":[78],"corresponding":[80],"extraction.":[82],"Based":[83],"LDB,":[85],"present":[87],"two":[88],"models,":[90],"with":[91],"without":[93],"explicit":[94],"event":[96],"modeling,":[97],"scenes,":[100],"which":[102],"hidden":[104],"Markov":[105],"model":[106],"(HMM)":[107],"is":[108],"used":[109],"depict":[111],"characteristics":[113],"correlations":[115],"among":[116],"various":[117],"events":[118],"constitute":[120],"scene.":[122],"The":[123],"experimental":[124],"results":[125],"demonstrate":[126],"effectiveness":[128],"proposed":[131],"approach":[132],"classification.":[136]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":12},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}