{"id":"https://openalex.org/W3162320900","doi":"https://doi.org/10.1109/icassp39728.2021.9413498","title":"A Multi-Channel Temporal Attention Convolutional Neural Network Model for Environmental Sound Classification","display_name":"A Multi-Channel Temporal Attention Convolutional Neural Network Model for Environmental Sound Classification","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3162320900","doi":"https://doi.org/10.1109/icassp39728.2021.9413498","mag":"3162320900"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413498","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413498","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/A5100430217","display_name":"You Wang","orcid":"https://orcid.org/0000-0002-6917-2199"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"You Wang","raw_affiliation_strings":["School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, Georgia, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, Georgia, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017284885","display_name":"Chuyao Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chuyao Feng","raw_affiliation_strings":["School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, Georgia, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, Georgia, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033437141","display_name":"David V. Anderson","orcid":"https://orcid.org/0000-0002-8571-4613"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David V. Anderson","raw_affiliation_strings":["School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, Georgia, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, Georgia, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":2.7781,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.9101071,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"930","last_page":"934"},"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":0.9902999997138977,"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/T11665","display_name":"Animal Vocal Communication and Behavior","score":0.9882000088691711,"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":0.7440049648284912},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.6270098090171814},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6176396608352661},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5234959721565247},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.44698524475097656},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.42987412214279175},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41184136271476746},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07111331820487976},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.060512810945510864}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7440049648284912},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.6270098090171814},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6176396608352661},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5234959721565247},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.44698524475097656},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.42987412214279175},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41184136271476746},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07111331820487976},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.060512810945510864},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413498","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413498","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5199999809265137,"display_name":"Life in Land","id":"https://metadata.un.org/sdg/15"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1514535095","https://openalex.org/W1972567154","https://openalex.org/W2052666245","https://openalex.org/W2113278353","https://openalex.org/W2133564696","https://openalex.org/W2292996718","https://openalex.org/W2509065397","https://openalex.org/W2562607067","https://openalex.org/W2593116425","https://openalex.org/W2745357708","https://openalex.org/W2791956393","https://openalex.org/W2883935097","https://openalex.org/W2884585870","https://openalex.org/W2901908104","https://openalex.org/W2937299048","https://openalex.org/W2962910554","https://openalex.org/W2963420686","https://openalex.org/W2963500860","https://openalex.org/W2963723765","https://openalex.org/W2964308564","https://openalex.org/W2972247414","https://openalex.org/W2972425456","https://openalex.org/W2982563264","https://openalex.org/W3095753917","https://openalex.org/W3098357269","https://openalex.org/W4295723153","https://openalex.org/W6623517193","https://openalex.org/W6630875275","https://openalex.org/W6679434410","https://openalex.org/W6743731764","https://openalex.org/W6749158954","https://openalex.org/W6752516136","https://openalex.org/W6753412334","https://openalex.org/W6756915875","https://openalex.org/W7046541945"],"related_works":["https://openalex.org/W1496222301","https://openalex.org/W3207760230","https://openalex.org/W1590307681","https://openalex.org/W4312814274","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703","https://openalex.org/W41015297","https://openalex.org/W4280645561"],"abstract_inverted_index":{"Recently,":[0],"many":[1],"attention-based":[2,157],"deep":[3],"neural":[4,47],"networks":[5],"have":[6],"emerged":[7],"and":[8,36,114,125,139,159],"achieved":[9],"state-of-the-art":[10],"performance":[11],"in":[12,83,102],"environmental":[13],"sound":[14],"classification.":[15],"The":[16,105],"essence":[17],"of":[18,28,66,122,147],"attention":[19,54,61,79,86,137],"mechanism":[20,62],"is":[21],"assigning":[22],"contribution":[23],"weights":[24],"on":[25],"different":[26,103],"parts":[27],"features,":[29],"namely":[30],"channels,":[31],"spectral":[32],"or":[33],"spatial":[34],"contents,":[35],"temporal":[37,53,60,74,78,100,136],"frames.":[38],"In":[39,127],"this":[40],"paper,":[41],"we":[42,150],"propose":[43],"an":[44],"effective":[45],"convolutional":[46],"network":[48,94],"structure":[49,80],"with":[50,119,143,154,163],"a":[51,59,84,164],"multichannel":[52],"(MCTA)":[55],"block,":[56],"which":[57,91],"applies":[58],"within":[63],"each":[64,89],"channel":[65],"the":[67,93,98,134,140,144],"embedded":[68],"features":[69],"to":[70,95,108],"extract":[71],"channel-wise":[72],"relevant":[73,99],"information.":[75],"This":[76],"multi-channel":[77],"will":[81],"result":[82],"distinct":[85],"vector":[87],"for":[88],"channel,":[90],"enables":[92],"fully":[96],"exploit":[97],"information":[101],"channels.":[104],"datasets":[106],"used":[107],"test":[109],"our":[110,128,152],"model":[111,138,142,153],"include":[112],"ESC-50":[113],"its":[115],"subset":[116],"ESC-10,":[117],"along":[118],"development":[120],"sets":[121],"DCASE":[123],"2018":[124],"2019.":[126],"experiments,":[129],"MCTA":[130],"performed":[131],"better":[132],"than":[133],"single-channel":[135],"non-attention":[141],"same":[145],"number":[146],"parameters.":[148],"Furthermore,":[149],"compared":[151],"some":[155],"successful":[156],"models":[158],"obtained":[160],"competitive":[161],"results":[162],"relatively":[165],"lighter":[166],"network.":[167]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":5}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}