{"id":"https://openalex.org/W2005122913","doi":"https://doi.org/10.1109/tasl.2012.2226160","title":"Image Feature Representation of the Subband Power Distribution for Robust Sound Event Classification","display_name":"Image Feature Representation of the Subband Power Distribution for Robust Sound Event Classification","publication_year":2012,"publication_date":"2012-10-23","ids":{"openalex":"https://openalex.org/W2005122913","doi":"https://doi.org/10.1109/tasl.2012.2226160","mag":"2005122913"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2012.2226160","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2012.2226160","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5070417199","display_name":"Jonathan Dennis","orcid":null},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jonathan Dennis","raw_affiliation_strings":["Institute for Infocomm Research, Agency for Science, Technology and Research, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, Agency for Science, Technology and Research, Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091485423","display_name":"Huy Dat Tran","orcid":"https://orcid.org/0000-0003-0223-6140"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Huy Dat Tran","raw_affiliation_strings":["Institute for Infocomm Research, Agency for Science, Technology and Research, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, Agency for Science, Technology and Research, Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070872826","display_name":"Eng Siong Chng","orcid":"https://orcid.org/0000-0001-6257-7399"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Eng Siong Chng","raw_affiliation_strings":["School of Computer Engineering, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.6046,"has_fulltext":false,"cited_by_count":83,"citation_normalized_percentile":{"value":0.97341764,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"21","issue":"2","first_page":"367","last_page":"377"},"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":0.9995999932289124,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.984499990940094,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.9249173402786255},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7252199053764343},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6546685695648193},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6312176585197449},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6119670867919922},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5825197696685791},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5809919834136963},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5380719304084778},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.44668281078338623},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.4383803606033325},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3935502767562866},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.26120078563690186}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.9249173402786255},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7252199053764343},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6546685695648193},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6312176585197449},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6119670867919922},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5825197696685791},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5809919834136963},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5380719304084778},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.44668281078338623},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.4383803606033325},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3935502767562866},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.26120078563690186},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tasl.2012.2226160","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2012.2226160","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.6800000071525574}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W200160492","https://openalex.org/W396690109","https://openalex.org/W1974387177","https://openalex.org/W1996160964","https://openalex.org/W2046972719","https://openalex.org/W2074354966","https://openalex.org/W2090431713","https://openalex.org/W2107542581","https://openalex.org/W2114806403","https://openalex.org/W2116681922","https://openalex.org/W2119662931","https://openalex.org/W2124714966","https://openalex.org/W2128653836","https://openalex.org/W2130322773","https://openalex.org/W2130640900","https://openalex.org/W2139689188","https://openalex.org/W2146083413","https://openalex.org/W2149241068","https://openalex.org/W2150866759","https://openalex.org/W2151103935","https://openalex.org/W2151407087","https://openalex.org/W2157277330","https://openalex.org/W2165163503","https://openalex.org/W2165712214","https://openalex.org/W2166742463","https://openalex.org/W2245569228","https://openalex.org/W2396233169","https://openalex.org/W2534708619","https://openalex.org/W4256068510","https://openalex.org/W6608239544","https://openalex.org/W6679040344","https://openalex.org/W6684249834","https://openalex.org/W6684426735","https://openalex.org/W6690610466","https://openalex.org/W6712002158"],"related_works":["https://openalex.org/W4312887852","https://openalex.org/W4317383455","https://openalex.org/W2548511587","https://openalex.org/W4293232884","https://openalex.org/W2422472940","https://openalex.org/W2019475500","https://openalex.org/W2548162870","https://openalex.org/W2144773493","https://openalex.org/W2138847091","https://openalex.org/W2786428026"],"abstract_inverted_index":{"The":[0,198],"ability":[1],"to":[2,78,127],"automatically":[3],"recognize":[4],"a":[5,46,75,101,128,161,169,184,192],"wide":[6],"range":[7,193,210],"of":[8,18,122,131,186,194,211],"sound":[9,44,81,189,212],"events":[10],"in":[11,85,113,216],"real-world":[12],"conditions":[13],"is":[14,39,91,204],"an":[15,51,145],"important":[16],"part":[17],"applications":[19],"such":[20],"as":[21,155],"acoustic":[22],"surveillance":[23],"and":[24,34,38,159,214],"machine":[25],"hearing.":[26],"Our":[27],"approach":[28,154,166],"takes":[29],"inspiration":[30],"from":[31,139,148],"both":[32,205],"audio":[33],"image":[35,52,67,99,146],"processing":[36],"fields,":[37],"based":[40,92,167],"on":[41,64,93,168,183],"transforming":[42],"the":[43,58,65,80,94,107,118,123,132,140,149,152,157,202,208],"into":[45],"two-dimensional":[47,103],"representation,":[48],"then":[49,143],"extracting":[50],"feature":[53,68,147,164],"for":[54,60,156],"classification.":[55],"This":[56,90],"provided":[57],"motivation":[59],"our":[61],"previous":[62],"work":[63],"spectrogram":[66,124],"(SIF).":[69],"In":[70],"this":[71],"paper,":[72],"we":[73],"propose":[74],"novel":[76,102,162],"method":[77],"improve":[79],"event":[82],"classification":[83,165],"performance":[84],"severe":[86,217],"mismatched":[87],"noise":[88,196],"conditions.":[89,197],"subband":[95],"power":[96,109],"distribution":[97,110],"(SPD)":[98],"-":[100],"representation":[104],"that":[105,201],"characterizes":[106],"spectral":[108],"over":[111,191,207],"time":[112],"each":[114],"frequency":[115],"subband.":[116],"Here,":[117],"high-powered":[119],"reliable":[120],"elements":[121],"are":[125],"transformed":[126],"localized":[129],"region":[130],"SPD,":[133,150],"hence":[134],"can":[135],"be":[136],"easily":[137],"separated":[138],"noise.":[141,219],"We":[142,178],"extract":[144],"using":[151],"same":[153],"SIF,":[158],"develop":[160],"missing":[163],"nearest":[170],"neighbor":[171],"classifier":[172],"(":[173],"<i":[174],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[175],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">k</i>":[176],"NN).":[177],"carry":[179],"out":[180],"comprehensive":[181],"experiments":[182],"database":[185],"50":[187],"environmental":[188],"classes":[190],"challenging":[195],"results":[199],"demonstrate":[200],"SPD-IF":[203],"discriminative":[206],"broad":[209],"classes,":[213],"robust":[215],"non-stationary":[218]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":13},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}