{"id":"https://openalex.org/W3011165840","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023099","title":"A Multi-feature Fusion Based Method For Urban Sound Tagging","display_name":"A Multi-feature Fusion Based Method For Urban Sound Tagging","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W3011165840","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023099","mag":"3011165840"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc47483.2019.9023099","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023099","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5027263923","display_name":"Jisheng Bai","orcid":"https://orcid.org/0000-0002-9803-8212"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jisheng Bai","raw_affiliation_strings":["School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100418487","display_name":"Chen Chen","orcid":"https://orcid.org/0000-0002-7242-6233"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Chen","raw_affiliation_strings":["School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065376714","display_name":"Jianfeng Chen","orcid":"https://orcid.org/0000-0002-7281-7138"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianfeng Chen","raw_affiliation_strings":["School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5027263923"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":0.6634,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.70762244,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1313","last_page":"1317"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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/T11692","display_name":"Noise Effects and Management","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/3616","display_name":"Speech and Hearing"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9979000091552734,"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/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.786064624786377},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7336492538452148},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.7327526211738586},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6631578803062439},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6432340741157532},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5845094919204712},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5338811874389648},{"id":"https://openalex.org/keywords/short-time-fourier-transform","display_name":"Short-time Fourier transform","score":0.4724082350730896},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.44289979338645935},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4410555362701416},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4407990574836731},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.43610015511512756},{"id":"https://openalex.org/keywords/environmental-noise","display_name":"Environmental noise","score":0.42049640417099},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.33910655975341797},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.181075781583786},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09305673837661743},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.07524725794792175},{"id":"https://openalex.org/keywords/fourier-analysis","display_name":"Fourier analysis","score":0.06609031558036804}],"concepts":[{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.786064624786377},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7336492538452148},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7327526211738586},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6631578803062439},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6432340741157532},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5845094919204712},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5338811874389648},{"id":"https://openalex.org/C166386157","wikidata":"https://www.wikidata.org/wiki/Q1477735","display_name":"Short-time Fourier transform","level":4,"score":0.4724082350730896},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.44289979338645935},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4410555362701416},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4407990574836731},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.43610015511512756},{"id":"https://openalex.org/C86781634","wikidata":"https://www.wikidata.org/wiki/Q2478325","display_name":"Environmental noise","level":3,"score":0.42049640417099},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.33910655975341797},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.181075781583786},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09305673837661743},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.07524725794792175},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.06609031558036804},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","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/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc47483.2019.9023099","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023099","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities","score":0.8399999737739563}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1496704041","https://openalex.org/W1561135842","https://openalex.org/W1686810756","https://openalex.org/W1836465849","https://openalex.org/W2008415856","https://openalex.org/W2036339641","https://openalex.org/W2114560218","https://openalex.org/W2123843894","https://openalex.org/W2149054612","https://openalex.org/W2183341477","https://openalex.org/W2509065397","https://openalex.org/W2751116311","https://openalex.org/W2883135409","https://openalex.org/W2889009082","https://openalex.org/W2897282582","https://openalex.org/W2912056372","https://openalex.org/W2963703618","https://openalex.org/W3098357269","https://openalex.org/W4289329167","https://openalex.org/W6681810270","https://openalex.org/W6743446608","https://openalex.org/W6743647910","https://openalex.org/W6754508767"],"related_works":["https://openalex.org/W2120540196","https://openalex.org/W3095343173","https://openalex.org/W2381036744","https://openalex.org/W2288135719","https://openalex.org/W2323749021","https://openalex.org/W2533590149","https://openalex.org/W2901989338","https://openalex.org/W82005754","https://openalex.org/W2334448276","https://openalex.org/W3210733254"],"abstract_inverted_index":{"Noise":[0],"pollution":[1,72],"is":[2,13,73,102,112],"one":[3],"of":[4,19,71,124,130],"the":[5,17,106,115,127],"serious":[6],"issues":[7],"for":[8,21,25,52],"citizens.":[9],"Mapping":[10],"urban":[11,39,53],"noise":[12,70],"essential":[14],"to":[15,37,67,104],"improve":[16],"quality":[18],"life":[20],"residents":[22],"and":[23,62,85,119],"construction":[24],"smart":[26],"cities.":[27],"Yet,":[28],"most":[29],"cities":[30],"lack":[31],"effective":[32],"classification":[33],"or":[34],"tagging":[35,55],"methods":[36],"monitor":[38],"noise.":[40],"To":[41],"tackle":[42],"this":[43],"challenge,":[44],"we":[45],"propose":[46],"a":[47,76,99,121],"multi-feature":[48],"fusion":[49,100],"based":[50],"method":[51,58,101,111],"sound":[54],"(UST).":[56],"This":[57],"combines":[59],"various":[60],"features":[61],"Convolutional":[63],"Neural":[64],"Networks":[65],"(CNNs)":[66],"predict":[68],"whether":[69],"present":[74],"in":[75],"10-second":[77],"recording.":[78],"Log-Mel,":[79],"harmonic,":[80],"short-time":[81],"Fourier":[82],"transform":[83],"(STFT)":[84],"Mel":[86],"Frequency":[87],"Cepstral":[88],"Coefficents":[89],"(MFCC)":[90],"spectrograms":[91],"are":[92],"fed":[93],"into":[94],"different":[95],"CNN":[96],"architectures.":[97],"And":[98],"applied":[103],"make":[105],"final":[107],"outputs.":[108],"The":[109],"proposed":[110],"evaluated":[113],"on":[114],"DCASE2019":[116],"task5":[117],"dataset":[118],"achieves":[120],"macro-AUPRC":[122],"score":[123],"0.68,":[125],"outperforming":[126],"baseline":[128],"system":[129],"0.54.":[131]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}