{"id":"https://openalex.org/W2074010570","doi":"https://doi.org/10.1109/apsipa.2014.7041646","title":"Enhanced local feature approach for overlapping sound event recognition","display_name":"Enhanced local feature approach for overlapping sound event recognition","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W2074010570","doi":"https://doi.org/10.1109/apsipa.2014.7041646","mag":"2074010570"},"language":"en","primary_location":{"id":"doi:10.1109/apsipa.2014.7041646","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2014.7041646","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Signal and Information Processing Association Annual Summit and Conference (APSIPA), 2014 Asia-Pacific","raw_type":"proceedings-article"},"type":"conference-paper","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, A*STAR, Singapore","Institute for Infocomm Research, A\u2217STAR 1 Fusionopolis Way, Singapore 138632"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, A*STAR, Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]},{"raw_affiliation_string":"Institute for Infocomm Research, A\u2217STAR 1 Fusionopolis Way, Singapore 138632","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"last","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, A*STAR, Singapore","Institute for Infocomm Research, A\u2217STAR 1 Fusionopolis Way, Singapore 138632"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, A*STAR, Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]},{"raw_affiliation_string":"Institute for Infocomm Research, A\u2217STAR 1 Fusionopolis Way, Singapore 138632","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"2","issue":null,"first_page":"1","last_page":"4"},"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":0.9995999932289124,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9830999970436096,"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/spectrogram","display_name":"Spectrogram","score":0.9437580704689026},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7613655924797058},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6717031598091125},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6440290212631226},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5559890270233154},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5515088438987732},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5440056920051575},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5277410745620728},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5163708925247192},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5097091197967529},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.4995551109313965},{"id":"https://openalex.org/keywords/voting","display_name":"Voting","score":0.4529423415660858},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.4379439353942871},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4242994785308838},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.41023266315460205},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.1758791208267212},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08318674564361572},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.08167067170143127}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.9437580704689026},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7613655924797058},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6717031598091125},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6440290212631226},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5559890270233154},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5515088438987732},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5440056920051575},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5277410745620728},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5163708925247192},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5097091197967529},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.4995551109313965},{"id":"https://openalex.org/C520049643","wikidata":"https://www.wikidata.org/wiki/Q189760","display_name":"Voting","level":3,"score":0.4529423415660858},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.4379439353942871},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4242994785308838},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.41023266315460205},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.1758791208267212},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08318674564361572},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.08167067170143127},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/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/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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipa.2014.7041646","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2014.7041646","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Signal and Information Processing Association Annual Summit and Conference (APSIPA), 2014 Asia-Pacific","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W22745672","https://openalex.org/W44831635","https://openalex.org/W1974387177","https://openalex.org/W1986315484","https://openalex.org/W2046972719","https://openalex.org/W2047710799","https://openalex.org/W2074764925","https://openalex.org/W2075076415","https://openalex.org/W2119110418","https://openalex.org/W2130322773","https://openalex.org/W2165163503","https://openalex.org/W2168373637","https://openalex.org/W2186582651","https://openalex.org/W2245569228","https://openalex.org/W2331166300","https://openalex.org/W6684426735","https://openalex.org/W6690610466","https://openalex.org/W6702387769"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W2942893872","https://openalex.org/W3127543252","https://openalex.org/W2065606036","https://openalex.org/W2016904525"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,36,56],"propose":[4,57],"a":[5,38,69,92,119,135],"feature-based":[6],"approach":[7,23,78],"to":[8,58],"address":[9],"the":[10,43,46,60,63,82,101,114],"challenging":[11,93],"task":[12],"of":[13,42,95,103,122],"recognising":[14],"overlapping":[15,97],"sound":[16,98],"events":[17],"from":[18,62],"single":[19],"channel":[20],"audio.":[21],"Our":[22],"is":[24,134],"based":[25],"on":[26,30,91],"our":[27,139],"previous":[28,83,140],"work":[29],"Local":[31],"Spectrogram":[32],"Features":[33],"(LSFs),":[34],"where":[35],"combined":[37],"local":[39],"spectral":[40],"representation":[41],"spectrogram":[44],"with":[45,100],"Generalised":[47],"Hough":[48],"Transform":[49],"(GHT)":[50],"voting":[51],"system":[52,116],"for":[53,71],"recognition.":[54],"Here":[55],"take":[59],"output":[61],"GHT":[64],"and":[65,73,107,124,128],"use":[66],"it":[67],"as":[68],"feature":[70],"classification,":[72],"demonstrate":[74],"that":[75,113],"such":[76],"an":[77],"can":[79,117],"improve":[80],"upon":[81],"knowledge-based":[84],"scoring":[85],"system.":[86],"Experiments":[87],"are":[88],"carried":[89],"out":[90],"set":[94],"five":[96],"events,":[99],"addition":[102],"non-stationary":[104],"background":[105],"noise":[106,130],"volume":[108],"change.":[109],"The":[110],"results":[111],"show":[112],"proposed":[115],"achieve":[118],"detection":[120],"rate":[121],"99%":[123],"91%":[125],"in":[126],"clean":[127],"0dB":[129],"conditions":[131],"respectively,":[132],"which":[133],"strong":[136],"improvement":[137],"over":[138],"work.":[141]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}