{"id":"https://openalex.org/W4226377790","doi":"https://doi.org/10.1109/tcds.2022.3160168","title":"Multimodal Urban Sound Tagging With Spatiotemporal Context","display_name":"Multimodal Urban Sound Tagging With Spatiotemporal Context","publication_year":2022,"publication_date":"2022-03-17","ids":{"openalex":"https://openalex.org/W4226377790","doi":"https://doi.org/10.1109/tcds.2022.3160168"},"language":"en","primary_location":{"id":"doi:10.1109/tcds.2022.3160168","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcds.2022.3160168","pdf_url":null,"source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"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 Cognitive and Developmental Systems","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2011.00175","any_repository_has_fulltext":true},"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":false,"raw_author_name":"Jisheng Bai","raw_affiliation_strings":["School of Marine Science and Technology, Northwestern Polytechnical University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0002-9803-8212","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/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"],"raw_orcid":null,"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/A5103175728","display_name":"Mou Wang","orcid":"https://orcid.org/0000-0002-6476-2501"},"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":"Mou Wang","raw_affiliation_strings":["School of Marine Science and Technology, Northwestern Polytechnical University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0002-6476-2501","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":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":1.6968,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.83547648,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"15","issue":"2","first_page":"555","last_page":"565"},"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/T11692","display_name":"Noise Effects and Management","score":0.9977999925613403,"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":0.9973999857902527,"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/computer-science","display_name":"Computer science","score":0.8521208763122559},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.7789309024810791},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.675137996673584},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5779418349266052},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5260760188102722},{"id":"https://openalex.org/keywords/multimodality","display_name":"Multimodality","score":0.5174130201339722},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4510502219200134},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4351653456687927},{"id":"https://openalex.org/keywords/spatial-contextual-awareness","display_name":"Spatial contextual awareness","score":0.4181517958641052}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8521208763122559},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7789309024810791},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.675137996673584},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5779418349266052},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5260760188102722},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.5174130201339722},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4510502219200134},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4351653456687927},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.4181517958641052},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcds.2022.3160168","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcds.2022.3160168","pdf_url":null,"source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"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 Cognitive and Developmental Systems","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2011.00175","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.00175","pdf_url":"https://arxiv.org/pdf/2011.00175","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2011.00175","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.00175","pdf_url":"https://arxiv.org/pdf/2011.00175","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities","score":0.5099999904632568},{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.4000000059604645}],"awards":[{"id":"https://openalex.org/G2105856630","display_name":"\u6b63\u4ea4\u65f6\u9891\u7a7a\u95f4\u8c03\u5236\u79fb\u52a8\u6c34\u58f0\u901a\u4fe1\u6280\u672f\u7814\u7a76","funder_award_id":"62071383","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2374318572","display_name":null,"funder_award_id":"U1609204","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8181528132","display_name":null,"funder_award_id":"61501374","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W154472438","https://openalex.org/W1133916940","https://openalex.org/W1496704041","https://openalex.org/W1561135842","https://openalex.org/W1836465849","https://openalex.org/W1921523184","https://openalex.org/W1970787564","https://openalex.org/W1996160964","https://openalex.org/W2036339641","https://openalex.org/W2038484192","https://openalex.org/W2045528981","https://openalex.org/W2102381657","https://openalex.org/W2114560218","https://openalex.org/W2123843894","https://openalex.org/W2130640900","https://openalex.org/W2156303437","https://openalex.org/W2184188583","https://openalex.org/W2194775991","https://openalex.org/W2509065397","https://openalex.org/W2526050071","https://openalex.org/W2548358476","https://openalex.org/W2566935005","https://openalex.org/W2567070169","https://openalex.org/W2591013610","https://openalex.org/W2593116425","https://openalex.org/W2598673810","https://openalex.org/W2736814566","https://openalex.org/W2751116311","https://openalex.org/W2765407302","https://openalex.org/W2767290858","https://openalex.org/W2795275057","https://openalex.org/W2799258971","https://openalex.org/W2888469011","https://openalex.org/W2912056372","https://openalex.org/W2917472217","https://openalex.org/W2936774411","https://openalex.org/W2939574508","https://openalex.org/W2966797067","https://openalex.org/W2982325051","https://openalex.org/W2982480602","https://openalex.org/W3011165840","https://openalex.org/W3011736257","https://openalex.org/W3043052463","https://openalex.org/W3085893206","https://openalex.org/W3094550259","https://openalex.org/W3098357269","https://openalex.org/W4256604311","https://openalex.org/W4288375019","https://openalex.org/W4289329167","https://openalex.org/W6606244218","https://openalex.org/W6633727632","https://openalex.org/W6638667902","https://openalex.org/W6640185926","https://openalex.org/W6682864246","https://openalex.org/W6686207219","https://openalex.org/W6731370813","https://openalex.org/W6743647910","https://openalex.org/W6745136726","https://openalex.org/W6753516609","https://openalex.org/W6761152316","https://openalex.org/W6766785157","https://openalex.org/W6780618053","https://openalex.org/W6783078499"],"related_works":["https://openalex.org/W4205899436","https://openalex.org/W2462138927","https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2088854863","https://openalex.org/W3111427900","https://openalex.org/W4302009627","https://openalex.org/W2011227383","https://openalex.org/W2897924318","https://openalex.org/W2138997758"],"abstract_inverted_index":{"Noise":[0],"pollution":[1],"significantly":[2],"affects":[3],"our":[4],"daily":[5],"life":[6],"and":[7,23,39,51,80,115],"urban":[8,25],"development.":[9],"Urban":[10],"sound":[11,43,129],"tagging":[12],"(UST)":[13],"has":[14,58],"attracted":[15],"much":[16],"attention":[17],"recently,":[18],"which":[19,45],"aims":[20],"to":[21,86,120,141],"analyze":[22],"monitor":[24],"noise":[26],"pollution.":[27],"One":[28],"weakness":[29],"of":[30,42,90,96,105,124,146,159,166],"the":[31,37,53,78,88,103,110,122,144,150,154,164,167],"previous":[32],"UST":[33,73,155],"studies":[34],"is":[35,113,136],"that":[36,75],"spatial":[38],"temporal":[40],"context":[41,82,112],"signals,":[44],"contains":[46],"complementary":[47],"information":[48],"about":[49],"when":[50],"where":[52],"audio":[54,79],"data":[55,133],"was":[56],"recorded,":[57],"not":[59],"been":[60],"investigated.":[61],"To":[62],"address":[63],"this":[64,67],"problem,":[65],"in":[66,138],"article,":[68],"we":[69],"propose":[70],"a":[71,132],"multimodal":[72,125],"system":[74],"deeply":[76],"mines":[77],"spatiotemporal":[81,111],"together.":[83],"In":[84],"order":[85],"incorporate":[87],"characteristics":[89],"different":[91],"acoustic":[92,118],"features,":[93],"two":[94],"sets":[95],"four":[97],"spectrograms":[98],"are":[99],"first":[100],"extracted":[101],"as":[102],"inputs":[104],"residual":[106],"neural":[107],"networks.":[108],"Then,":[109],"encoded":[114],"combined":[116],"with":[117],"features":[119],"explore":[121],"efficiency":[123],"learning":[126],"for":[127],"discriminating":[128],"signals.":[130],"Moreover,":[131],"filtering":[134],"approach":[135],"adopted":[137],"text":[139],"processing":[140],"further":[142],"improve":[143],"performance":[145],"multimodality.":[147],"We":[148],"evaluate":[149],"proposed":[151,168],"method":[152],"on":[153],"challenge":[156],"(task":[157],"5)":[158],"DCASE2020.":[160],"Experimental":[161],"results":[162],"demonstrate":[163],"effectiveness":[165],"method.":[169]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}