{"id":"https://openalex.org/W4312765536","doi":"https://doi.org/10.1109/tcds.2022.3222350","title":"A Squeeze-and-Excitation and Transformer-Based Cross-Task Model for Environmental Sound Recognition","display_name":"A Squeeze-and-Excitation and Transformer-Based Cross-Task Model for Environmental Sound Recognition","publication_year":2022,"publication_date":"2022-11-15","ids":{"openalex":"https://openalex.org/W4312765536","doi":"https://doi.org/10.1109/tcds.2022.3222350"},"language":"en","primary_location":{"id":"doi:10.1109/tcds.2022.3222350","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcds.2022.3222350","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":["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":false,"raw_author_name":"Jisheng Bai","raw_affiliation_strings":["Joint Laboratory of Environmental Sound Sensing, School of Marine Science and Technology, Northwestern Polytechnical University, Xi’an, China","LianFeng Acoustic Technologies Company Ltd, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0002-9803-8212","affiliations":[{"raw_affiliation_string":"Joint Laboratory of Environmental Sound Sensing, School of Marine Science and Technology, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"LianFeng Acoustic Technologies Company Ltd, Xi'an, China","institution_ids":[]}]},{"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":["Joint Laboratory of Environmental Sound Sensing, School of Marine Science and Technology, Northwestern Polytechnical University, Xi’an, China","LianFeng Acoustic Technologies Company Ltd, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Joint Laboratory of Environmental Sound Sensing, School of Marine Science and Technology, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"LianFeng Acoustic Technologies Company Ltd, Xi'an, China","institution_ids":[]}]},{"author_position":"middle","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":["Joint Laboratory of Environmental Sound Sensing, School of Marine Science and Technology, Northwestern Polytechnical University, Xi’an, China","LianFeng Acoustic Technologies Company Ltd, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0002-6476-2501","affiliations":[{"raw_affiliation_string":"Joint Laboratory of Environmental Sound Sensing, School of Marine Science and Technology, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"LianFeng Acoustic Technologies Company Ltd, Xi'an, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001938465","display_name":"Muhammad Saad Ayub","orcid":"https://orcid.org/0000-0002-0452-8457"},"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":"Muhammad Saad Ayub","raw_affiliation_strings":["Joint Laboratory of Environmental Sound Sensing, School of Marine Science and Technology, Northwestern Polytechnical University, Xi’an, China","LianFeng Acoustic Technologies Company Ltd, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0002-0452-8457","affiliations":[{"raw_affiliation_string":"Joint Laboratory of Environmental Sound Sensing, School of Marine Science and Technology, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"LianFeng Acoustic Technologies Company Ltd, Xi'an, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017201798","display_name":"Qingli Yan","orcid":"https://orcid.org/0000-0003-0689-145X"},"institutions":[{"id":"https://openalex.org/I4210136859","display_name":"Xi\u2019an University of Posts and Telecommunications","ror":"https://ror.org/04jn0td46","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210136859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingli Yan","raw_affiliation_strings":["School of Computer Science and Technology, Xi’an University of Posts and Telecommunications, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0003-0689-145X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xi’an University of Posts and Telecommunications, Xi’an, China","institution_ids":["https://openalex.org/I4210136859"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9796,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.86559803,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"15","issue":"3","first_page":"1501","last_page":"1513"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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":1.0,"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":0.9980999827384949,"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":0.98580002784729,"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":0.8226885795593262},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.744114339351654},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5701490640640259},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5580228567123413},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5161584615707397},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3871781527996063},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.0767492949962616}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8226885795593262},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.744114339351654},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5701490640640259},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5580228567123413},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5161584615707397},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3871781527996063},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0767492949962616},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcds.2022.3222350","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcds.2022.3222350","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"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities","score":0.4399999976158142}],"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"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W2056500480","https://openalex.org/W2086384421","https://openalex.org/W2103235956","https://openalex.org/W2117361667","https://openalex.org/W2183341477","https://openalex.org/W2346794446","https://openalex.org/W2604293017","https://openalex.org/W2736814566","https://openalex.org/W2741049562","https://openalex.org/W2746314669","https://openalex.org/W2752782242","https://openalex.org/W2759976799","https://openalex.org/W2775794021","https://openalex.org/W2883939359","https://openalex.org/W2886877375","https://openalex.org/W2896457183","https://openalex.org/W2900315145","https://openalex.org/W2912056372","https://openalex.org/W2921511952","https://openalex.org/W2936774411","https://openalex.org/W2952218014","https://openalex.org/W2957789971","https://openalex.org/W2982325051","https://openalex.org/W3049446265","https://openalex.org/W3082878506","https://openalex.org/W3083566224","https://openalex.org/W3085893206","https://openalex.org/W3094550259","https://openalex.org/W3097777922","https://openalex.org/W3099330747","https://openalex.org/W3111552472","https://openalex.org/W3162150435","https://openalex.org/W3165945839","https://openalex.org/W3170230444","https://openalex.org/W3178592608","https://openalex.org/W3184890107","https://openalex.org/W3196324719","https://openalex.org/W3197827948","https://openalex.org/W3208624098","https://openalex.org/W3209572141","https://openalex.org/W4224923672","https://openalex.org/W4226377790","https://openalex.org/W4236333699","https://openalex.org/W4256604311","https://openalex.org/W4288375019","https://openalex.org/W4394662183","https://openalex.org/W6630111507","https://openalex.org/W6634555756","https://openalex.org/W6679436768","https://openalex.org/W6736350746","https://openalex.org/W6743428213","https://openalex.org/W6745136726","https://openalex.org/W6753847621","https://openalex.org/W6755207826","https://openalex.org/W6758876586","https://openalex.org/W6761152316","https://openalex.org/W6765212446","https://openalex.org/W6779341498","https://openalex.org/W6779565119","https://openalex.org/W6779961064","https://openalex.org/W6780226713","https://openalex.org/W6783078499","https://openalex.org/W6784333009","https://openalex.org/W6796250704","https://openalex.org/W6864909175"],"related_works":["https://openalex.org/W4390516098","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W2142795561","https://openalex.org/W4205302943","https://openalex.org/W2561132942","https://openalex.org/W3155418658","https://openalex.org/W4243199227","https://openalex.org/W2379948177","https://openalex.org/W2119949815"],"abstract_inverted_index":{"Environmental":[0],"sound":[1,80,85],"recognition":[2],"(ESR)":[3],"is":[4,91,115],"an":[5],"emerging":[6],"research":[7],"topic":[8],"in":[9,24],"audio":[10],"pattern":[11],"recognition.":[12],"Many":[13],"tasks":[14,71,132],"are":[15,30,37,133],"presented":[16,92],"to":[17,19,42,102],"resort":[18],"computational":[20],"models":[21,29],"for":[22,33,68,129],"ESR":[23,179],"real-life":[25],"applications.":[26],"However,":[27],"current":[28],"usually":[31],"designed":[32],"individual":[34],"tasks,":[35,54],"and":[36,40,82,98,107,141,146],"not":[38,56],"robust":[39],"applicable":[41],"other":[43],"tasks.":[44,163,180],"Cross-task":[45],"models,":[46],"which":[47],"promote":[48],"unified":[49],"knowledge":[50,176],"modeling":[51],"across":[52,177],"various":[53],"have":[55],"been":[57],"thoroughly":[58],"investigated.":[59],"In":[60],"this":[61],"article,":[62],"we":[63],"propose":[64],"a":[65],"cross-task":[66,156,170],"model":[67,157,171],"three":[69,131],"different":[70,178],"of":[72,110,126,139,143],"ESR:":[73],"1)":[74],"acoustic":[75,112,144,175],"scene":[76],"classification;":[77],"2)":[78],"urban":[79],"tagging;":[81],"3)":[83],"anomalous":[84],"detection.":[86],"An":[87],"architecture":[88],"named":[89],"SE-Trans":[90],"that":[93,122,153,167],"uses":[94],"attention":[95],"mechanism-based":[96],"Squeeze-and-Excitation":[97],"Transformer":[99],"encoder":[100],"modules":[101],"learn":[103],"the":[104,111,118,124,130,136,154,168],"channelwise":[105],"relationship":[106],"temporal":[108],"dependencies":[109],"features.":[113],"FMix":[114],"employed":[116],"as":[117],"data":[119],"augmentation":[120],"method":[121],"improves":[123],"performance":[125,160],"ESR.":[127],"Evaluations":[128],"conducted":[134],"on":[135,161],"recent":[137],"databases":[138],"detection":[140],"classification":[142],"scenes":[145],"event":[147],"challenges.":[148],"The":[149],"experimental":[150],"results":[151],"show":[152],"proposed":[155,169],"achieves":[158],"state-of-the-art":[159],"all":[162],"Further":[164],"analysis":[165],"demonstrates":[166],"can":[172],"effectively":[173],"utilize":[174]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2023-01-05T00:00:00"}