{"id":"https://openalex.org/W3015855451","doi":"https://doi.org/10.1109/icassp40776.2020.9053194","title":"Time-Frequency Feature Decomposition Based on Sound Duration for Acoustic Scene Classification","display_name":"Time-Frequency Feature Decomposition Based on Sound Duration for Acoustic Scene Classification","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015855451","doi":"https://doi.org/10.1109/icassp40776.2020.9053194","mag":"3015855451"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053194","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053194","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5113876348","display_name":"Yuzhong Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuzhong Wu","raw_affiliation_strings":["Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001795601","display_name":"Tan Lee","orcid":"https://orcid.org/0000-0002-7089-3436"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tan Lee","raw_affiliation_strings":["Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5113876348"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":1.6669,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.84213298,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"716","last_page":"720"},"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":0.9968000054359436,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9805999994277954,"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":0.6885381937026978},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6057931184768677},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5990595817565918},{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.5922161936759949},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.580681324005127},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5532790422439575},{"id":"https://openalex.org/keywords/wavelet","display_name":"Wavelet","score":0.5339615941047668},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5308234095573425},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.5170972347259521},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5101340413093567},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4900461435317993},{"id":"https://openalex.org/keywords/time\u2013frequency-analysis","display_name":"Time\u2013frequency analysis","score":0.48773226141929626},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4855179786682129},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4526765048503876},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.43875208497047424},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.4319920241832733},{"id":"https://openalex.org/keywords/bioacoustics","display_name":"Bioacoustics","score":0.41237854957580566},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3297822177410126},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.18509754538536072},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.11856025457382202}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6885381937026978},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6057931184768677},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5990595817565918},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.5922161936759949},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.580681324005127},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5532790422439575},{"id":"https://openalex.org/C47432892","wikidata":"https://www.wikidata.org/wiki/Q831390","display_name":"Wavelet","level":2,"score":0.5339615941047668},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5308234095573425},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.5170972347259521},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5101340413093567},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4900461435317993},{"id":"https://openalex.org/C142433447","wikidata":"https://www.wikidata.org/wiki/Q7806653","display_name":"Time\u2013frequency analysis","level":3,"score":0.48773226141929626},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4855179786682129},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4526765048503876},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.43875208497047424},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.4319920241832733},{"id":"https://openalex.org/C34951282","wikidata":"https://www.wikidata.org/wiki/Q864191","display_name":"Bioacoustics","level":2,"score":0.41237854957580566},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3297822177410126},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.18509754538536072},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.11856025457382202},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"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/icassp40776.2020.9053194","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053194","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1496437685","https://openalex.org/W1561135842","https://openalex.org/W2013824652","https://openalex.org/W2076608692","https://openalex.org/W2163605009","https://openalex.org/W2765407302","https://openalex.org/W2883935097","https://openalex.org/W2907743838","https://openalex.org/W2936222847","https://openalex.org/W2957789971","https://openalex.org/W2982683041","https://openalex.org/W3027138507","https://openalex.org/W4289096690","https://openalex.org/W4295723153","https://openalex.org/W6633727632","https://openalex.org/W6684191040","https://openalex.org/W6745136726","https://openalex.org/W6752516136","https://openalex.org/W6757542112","https://openalex.org/W6765212446","https://openalex.org/W7046541945"],"related_works":["https://openalex.org/W2289868279","https://openalex.org/W4315836293","https://openalex.org/W4231351862","https://openalex.org/W4212794605","https://openalex.org/W2970176078","https://openalex.org/W2098934641","https://openalex.org/W1975359510","https://openalex.org/W2088690926","https://openalex.org/W1526651343","https://openalex.org/W4387698063"],"abstract_inverted_index":{"Acoustic":[0],"scene":[1,115],"classification":[2,97],"is":[3,19,23,36],"the":[4,8,41,50,91,119],"task":[5],"of":[6,10,26,100,121,131],"identifying":[7],"type":[9],"acoustic":[11,114,132],"environment":[12],"in":[13],"which":[14],"a":[15,24,57],"given":[16],"audio":[17],"signal":[18,22],"recorded.":[20],"The":[21],"mixture":[25],"sound":[27,44,122],"events":[28],"with":[29],"various":[30],"characteristics.":[31],"In-depth":[32],"and":[33,48,66,76,83,117],"focused":[34],"analysis":[35],"needed":[37],"to":[38,71,95],"find":[39],"out":[40],"most":[42,111],"representative":[43],"patterns":[45],"for":[46,113,127],"recognizing":[47],"differentiating":[49],"scenes.":[51,133],"In":[52],"this":[53],"paper,":[54],"we":[55],"propose":[56],"feature":[58],"decomposition":[59],"method":[60,93],"based":[61,85],"on":[62,81],"temporal":[63],"median":[64],"filtering,":[65],"use":[67],"convolutional":[68],"neural":[69],"network":[70],"model":[72],"long-duration":[73,107],"background":[74],"sounds":[75,78,108],"transient":[77],"separately.":[79],"Experiments":[80],"log-mel":[82],"wavelet":[84],"time-frequency":[86],"features":[87],"show":[88],"that":[89,105],"using":[90],"proposed":[92],"leads":[94],"better":[96],"accuracy.":[98],"Analysis":[99],"detailed":[101],"experimental":[102],"results":[103],"reveals":[104],"(1)":[106],"are":[109],"generally":[110],"informative":[112],"classification;":[116],"(2)":[118],"focus":[120],"duration":[123],"may":[124],"be":[125],"different":[126,129],"classifying":[128],"types":[130]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}