{"id":"https://openalex.org/W2090431713","doi":"https://doi.org/10.1109/lsp.2010.2100380","title":"Spectrogram Image Feature for Sound Event Classification in Mismatched Conditions","display_name":"Spectrogram Image Feature for Sound Event Classification in Mismatched Conditions","publication_year":2010,"publication_date":"2010-12-22","ids":{"openalex":"https://openalex.org/W2090431713","doi":"https://doi.org/10.1109/lsp.2010.2100380","mag":"2090431713"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2010.2100380","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2010.2100380","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","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":["ASTAR Institute of Infocomm Research, Singapore","[A-star, Institute for Infocomm Research, Singapore, Singapore]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ASTAR Institute of Infocomm Research, Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]},{"raw_affiliation_string":"[A-star, Institute for Infocomm Research, Singapore, Singapore]","institution_ids":["https://openalex.org/I3005327000"]}]},{"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":["ASTAR Institute of Infocomm Research, Singapore","[A-star, Institute for Infocomm Research, Singapore, Singapore]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ASTAR Institute of Infocomm Research, Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]},{"raw_affiliation_string":"[A-star, Institute for Infocomm Research, Singapore, Singapore]","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"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":"Haizhou Li","raw_affiliation_strings":["ASTAR Institute of Infocomm Research, Singapore","[A-star, Institute for Infocomm Research, Singapore, Singapore]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ASTAR Institute of Infocomm Research, Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]},{"raw_affiliation_string":"[A-star, Institute for Infocomm Research, Singapore, Singapore]","institution_ids":["https://openalex.org/I3005327000"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.8618,"has_fulltext":false,"cited_by_count":211,"citation_normalized_percentile":{"value":0.9492183,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"18","issue":"2","first_page":"130","last_page":"133"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music 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/T11667","display_name":"Advanced Chemical Sensor Technologies","score":0.9922000169754028,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9894000291824341,"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":0.9000995755195618},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7093206644058228},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6605289578437805},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6145742535591125},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.6117867827415466},{"id":"https://openalex.org/keywords/grayscale","display_name":"Grayscale","score":0.5298654437065125},{"id":"https://openalex.org/keywords/monochrome","display_name":"Monochrome","score":0.49971842765808105},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4742138385772705},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4546055197715759},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4471054673194885},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.4274928867816925},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3561754524707794},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3414791524410248},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2751651406288147}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.9000995755195618},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7093206644058228},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6605289578437805},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6145742535591125},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.6117867827415466},{"id":"https://openalex.org/C78201319","wikidata":"https://www.wikidata.org/wiki/Q685727","display_name":"Grayscale","level":3,"score":0.5298654437065125},{"id":"https://openalex.org/C2776754580","wikidata":"https://www.wikidata.org/wiki/Q10770146","display_name":"Monochrome","level":2,"score":0.49971842765808105},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4742138385772705},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4546055197715759},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4471054673194885},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.4274928867816925},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3561754524707794},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3414791524410248},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2751651406288147},{"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/lsp.2010.2100380","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2010.2100380","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1554104313","https://openalex.org/W2069231281","https://openalex.org/W2118230268","https://openalex.org/W2132456362","https://openalex.org/W2139689188","https://openalex.org/W2165163503","https://openalex.org/W2914885528","https://openalex.org/W6633146083","https://openalex.org/W6684426735"],"related_works":["https://openalex.org/W2356040864","https://openalex.org/W2623088128","https://openalex.org/W294870043","https://openalex.org/W2530685530","https://openalex.org/W214368458","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W2132362409","https://openalex.org/W4200384795"],"abstract_inverted_index":{"In":[0],"this":[1],"letter,":[2],"we":[3],"present":[4],"a":[5,41,69,88,142,157,164,174],"novel":[6],"feature":[7],"extraction":[8],"method":[9,57,117,153],"for":[10,186],"sound":[11,161],"event":[12],"classification,":[13],"based":[14],"on":[15,156],"the":[16,21,29,50,100,110,115,120,123,130,134,137,147,184],"visual":[17],"signature":[18],"extracted":[19,107],"from":[20,28,119],"sound's":[22],"time-frequency":[23],"representation.":[24],"The":[25,52,62,73,92,112,152],"motivation":[26],"stems":[27],"fact":[30,121],"that":[31,36,122],"spectrograms":[32],"form":[33,87,109],"recognisable":[34],"images,":[35],"can":[37],"be":[38],"identified":[39],"by":[40,47],"human":[42],"reader,":[43],"with":[44,68],"perception":[45],"enhanced":[46],"pseudo-coloration":[48],"of":[49,81,114,136,159,166],"image.":[51,90],"signal":[53,131],"processing":[54],"in":[55,103,180],"our":[56],"is":[58,64,76,83,125,139,154],"as":[59],"follows.":[60],"1)":[61],"spectrogram":[63],"normalised":[65],"into":[66,78,97],"greyscale":[67],"fixed":[70],"range.":[71],"2)":[72],"dynamic":[74],"range":[75],"quantized":[77],"regions,":[79],"each":[80,104],"which":[82],"then":[84],"mapped":[85],"to":[86,108,141],"monochrome":[89,93],"3)":[91],"images":[94],"are":[95,106],"partitioned":[96],"blocks,":[98],"and":[99,132,169,172],"distribution":[101],"statistics":[102],"block":[105],"feature.":[111],"robustness":[113],"proposed":[116],"comes":[118],"noise":[124,138,187],"normally":[126],"more":[127],"diffuse":[128],"than":[129],"therefore":[133],"effect":[135],"limited":[140],"particular":[143],"quantization":[144],"region,":[145],"leaving":[146],"other":[148,178],"regions":[149],"less":[150],"changed.":[151],"tested":[155],"database":[158],"60":[160],"classes":[162],"containing":[163],"mixture":[165],"collision,":[167],"action":[168],"characteristic":[170],"sounds":[171],"shows":[173],"significant":[175],"improvement":[176],"over":[177],"methods":[179],"mismatched":[181],"conditions,":[182],"without":[183],"need":[185],"reduction.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":18},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":18},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":17},{"year":2019,"cited_by_count":30},{"year":2018,"cited_by_count":22},{"year":2017,"cited_by_count":19},{"year":2016,"cited_by_count":16},{"year":2015,"cited_by_count":16},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":7}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}
