{"id":"https://openalex.org/W4312290146","doi":"https://doi.org/10.1109/ijcnn55064.2022.9892839","title":"Investigation of Performance of Visual Attention Mechanisms for Environmental Sound Classification: A Comparative Study","display_name":"Investigation of Performance of Visual Attention Mechanisms for Environmental Sound Classification: A Comparative Study","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W4312290146","doi":"https://doi.org/10.1109/ijcnn55064.2022.9892839"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn55064.2022.9892839","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn55064.2022.9892839","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5005713107","display_name":"Achyut Mani Tripathi","orcid":"https://orcid.org/0000-0003-0548-9688"},"institutions":[{"id":"https://openalex.org/I1317621060","display_name":"Indian Institute of Technology Guwahati","ror":"https://ror.org/0022nd079","country_code":"IN","type":"education","lineage":["https://openalex.org/I1317621060"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Achyut Mani Tripathi","raw_affiliation_strings":["Indian Institute of Technology Guwahati,Department of Computer Science & Engineering,Guwahati,Assam,India,781039"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Guwahati,Department of Computer Science & Engineering,Guwahati,Assam,India,781039","institution_ids":["https://openalex.org/I1317621060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014658425","display_name":"Swarup Ranjan Behera","orcid":null},"institutions":[{"id":"https://openalex.org/I1317621060","display_name":"Indian Institute of Technology Guwahati","ror":"https://ror.org/0022nd079","country_code":"IN","type":"education","lineage":["https://openalex.org/I1317621060"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Swarup Ranjan Behera","raw_affiliation_strings":["Indian Institute of Technology Guwahati,Department of Computer Science & Engineering,Guwahati,Assam,India,781039"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Guwahati,Department of Computer Science & Engineering,Guwahati,Assam,India,781039","institution_ids":["https://openalex.org/I1317621060"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086500792","display_name":"Konark Paul","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Konark Paul","raw_affiliation_strings":["Independent Researcher,Banguluru,Karnataka,India","Independent Researcher, Banguluru, Karnataka, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Independent Researcher,Banguluru,Karnataka,India","institution_ids":[]},{"raw_affiliation_string":"Independent Researcher, Banguluru, Karnataka, India","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"102","issue":null,"first_page":"1","last_page":"8"},"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/T10788","display_name":"Neuroscience and Music Perception","score":0.9713000059127808,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11665","display_name":"Animal Vocal Communication and Behavior","score":0.9689000248908997,"subfield":{"id":"https://openalex.org/subfields/1309","display_name":"Developmental Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7428714036941528},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7196798324584961},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6405515074729919},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6102343797683716},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5961505174636841},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.44397613406181335},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4395887553691864},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.4128757417201996},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3866996765136719},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10251426696777344},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.06374266743659973}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7428714036941528},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7196798324584961},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6405515074729919},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6102343797683716},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5961505174636841},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.44397613406181335},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4395887553691864},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.4128757417201996},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3866996765136719},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10251426696777344},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.06374266743659973},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn55064.2022.9892839","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn55064.2022.9892839","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7200000286102295,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1501987291","https://openalex.org/W1972567154","https://openalex.org/W2052666245","https://openalex.org/W2745969942","https://openalex.org/W2751841560","https://openalex.org/W2884585870","https://openalex.org/W2919115771","https://openalex.org/W2922509574","https://openalex.org/W2937299048","https://openalex.org/W2945164022","https://openalex.org/W2963420686","https://openalex.org/W2964236337","https://openalex.org/W2968661326","https://openalex.org/W2972247414","https://openalex.org/W2982106364","https://openalex.org/W3012504141","https://openalex.org/W3025016330","https://openalex.org/W3083566224","https://openalex.org/W3094502228","https://openalex.org/W3095102709","https://openalex.org/W3095753917","https://openalex.org/W3118826611","https://openalex.org/W3119205652","https://openalex.org/W3162320900","https://openalex.org/W3162418282","https://openalex.org/W3171087525","https://openalex.org/W3177052299","https://openalex.org/W3181955139","https://openalex.org/W3189759539","https://openalex.org/W3196974791","https://openalex.org/W3206996142","https://openalex.org/W4295723153","https://openalex.org/W6643326691","https://openalex.org/W6743731764","https://openalex.org/W6752516136","https://openalex.org/W6753412334","https://openalex.org/W6765253218"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2130974462","https://openalex.org/W972276598","https://openalex.org/W2086519370","https://openalex.org/W2028665553","https://openalex.org/W2087343574","https://openalex.org/W2535915176","https://openalex.org/W2105860728","https://openalex.org/W4287657826"],"abstract_inverted_index":{"Classification":[0],"of":[1,11,59,77,91,97],"environmental":[2,65,106],"sound":[3,45,66,107],"is":[4,101],"an":[5],"equally":[6],"challenging":[7],"task":[8],"to":[9,31,63],"classification":[10,67,108],"human":[12],"speech":[13],"or":[14],"music.":[15],"In":[16,70],"recent":[17],"years,":[18],"attention":[19,24,84],"mechanism":[20],"has":[21],"gained":[22],"considerable":[23],"in":[25,48,88],"learning":[26],"representative":[27],"and":[28,44,112],"prototypical":[29],"features":[30],"resolve":[32],"various":[33],"research":[34],"challenges":[35],"from":[36],"domains":[37],"such":[38],"as":[39,68],"computer":[40,50],"vision,":[41],"text":[42],"mining":[43],"classification.":[46],"Advancements":[47],"the":[49,57,75,89,92,98],"vision":[51],"can":[52],"be":[53],"used":[54],"for":[55],"improving":[56],"performance":[58,76,96],"deep":[60,78,93,99],"models":[61],"designed":[62],"perform":[64],"well.":[69],"this":[71],"paper,":[72],"we":[73],"investigated":[74],"network":[79],"when":[80],"twelve":[81],"SOTA":[82],"visual":[83],"mechanisms":[85],"are":[86],"incorporated":[87],"training":[90],"network.":[94],"The":[95],"model":[100],"evaluated":[102],"on":[103],"two":[104],"benchmark":[105],"datasets,":[109],"viz.":[110],"ESC-10":[111],"DCASE-2019":[113],"task-1(A)":[114],"datasets.":[115]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}