{"id":"https://openalex.org/W4387298048","doi":"https://doi.org/10.1587/transfun.2023eal2056","title":"Dual-Path Convolutional Neural Network Based on Band Interaction Block for Acoustic Scene Classification","display_name":"Dual-Path Convolutional Neural Network Based on Band Interaction Block for Acoustic Scene Classification","publication_year":2023,"publication_date":"2023-10-03","ids":{"openalex":"https://openalex.org/W4387298048","doi":"https://doi.org/10.1587/transfun.2023eal2056"},"language":"en","primary_location":{"id":"doi:10.1587/transfun.2023eal2056","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transfun.2023eal2056","pdf_url":"https://www.jstage.jst.go.jp/article/transfun/advpub/0/advpub_2023EAL2056/_pdf","source":{"id":"https://openalex.org/S166990724","display_name":"IEICE Transactions on Fundamentals of Electronics Communications and Computer Sciences","issn_l":"0916-8508","issn":["0916-8508","1745-1337"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.jstage.jst.go.jp/article/transfun/advpub/0/advpub_2023EAL2056/_pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067420587","display_name":"Pengxu JIANG","orcid":"https://orcid.org/0000-0003-1738-1455"},"institutions":[{"id":"https://openalex.org/I4210090971","display_name":"Southeast University","ror":"https://ror.org/00cf0ab87","country_code":"BD","type":"education","lineage":["https://openalex.org/I4210090971"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Pengxu JIANG","raw_affiliation_strings":["School of Information Science and Engineering, Southeast University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Southeast University","institution_ids":["https://openalex.org/I4210090971"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100397465","display_name":"Yang Yang","orcid":"https://orcid.org/0000-0001-9172-1695"},"institutions":[{"id":"https://openalex.org/I4210090971","display_name":"Southeast University","ror":"https://ror.org/00cf0ab87","country_code":"BD","type":"education","lineage":["https://openalex.org/I4210090971"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Yang YANG","raw_affiliation_strings":["School of Information Science and Engineering, Southeast University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Southeast University","institution_ids":["https://openalex.org/I4210090971"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052217750","display_name":"Yue Xie","orcid":"https://orcid.org/0000-0002-5750-5873"},"institutions":[{"id":"https://openalex.org/I2799736854","display_name":"Nanjing Institute of Technology","ror":"https://ror.org/00n6txq60","country_code":"CN","type":"education","lineage":["https://openalex.org/I2799736854"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue XIE","raw_affiliation_strings":["School of Communication Engineering, Nanjing Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Communication Engineering, Nanjing Institute of Technology","institution_ids":["https://openalex.org/I2799736854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112110256","display_name":"Cairong Zou","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090971","display_name":"Southeast University","ror":"https://ror.org/00cf0ab87","country_code":"BD","type":"education","lineage":["https://openalex.org/I4210090971"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Cairong ZOU","raw_affiliation_strings":["School of Information Science and Engineering, Southeast University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Southeast University","institution_ids":["https://openalex.org/I4210090971"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082390057","display_name":"Qingyun WANG","orcid":null},"institutions":[{"id":"https://openalex.org/I2799736854","display_name":"Nanjing Institute of Technology","ror":"https://ror.org/00n6txq60","country_code":"CN","type":"education","lineage":["https://openalex.org/I2799736854"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingyun WANG","raw_affiliation_strings":["School of Communication Engineering, Nanjing Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Communication Engineering, Nanjing Institute of Technology","institution_ids":["https://openalex.org/I2799736854"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3479,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.54278367,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"E107.A","issue":"7","first_page":"1040","last_page":"1044"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"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":0.991100013256073,"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/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7766690850257874},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.7744073271751404},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7587028741836548},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6797357797622681},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.6498616337776184},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.5531806945800781},{"id":"https://openalex.org/keywords/radio-spectrum","display_name":"Radio spectrum","score":0.5426015257835388},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.5382715463638306},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5316382646560669},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5222445130348206},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4890311658382416},{"id":"https://openalex.org/keywords/frequency-band","display_name":"Frequency band","score":0.4113295376300812},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.32088449597358704},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.31763023138046265},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1255931258201599},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10894918441772461},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.06841641664505005},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.06023043394088745}],"concepts":[{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7766690850257874},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.7744073271751404},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7587028741836548},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6797357797622681},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.6498616337776184},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.5531806945800781},{"id":"https://openalex.org/C92545706","wikidata":"https://www.wikidata.org/wiki/Q902174","display_name":"Radio spectrum","level":2,"score":0.5426015257835388},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.5382715463638306},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5316382646560669},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5222445130348206},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4890311658382416},{"id":"https://openalex.org/C2778116611","wikidata":"https://www.wikidata.org/wiki/Q25110567","display_name":"Frequency band","level":3,"score":0.4113295376300812},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.32088449597358704},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.31763023138046265},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1255931258201599},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10894918441772461},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.06841641664505005},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.06023043394088745},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1587/transfun.2023eal2056","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transfun.2023eal2056","pdf_url":"https://www.jstage.jst.go.jp/article/transfun/advpub/0/advpub_2023EAL2056/_pdf","source":{"id":"https://openalex.org/S166990724","display_name":"IEICE Transactions on Fundamentals of Electronics Communications and Computer Sciences","issn_l":"0916-8508","issn":["0916-8508","1745-1337"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1587/transfun.2023eal2056","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transfun.2023eal2056","pdf_url":"https://www.jstage.jst.go.jp/article/transfun/advpub/0/advpub_2023EAL2056/_pdf","source":{"id":"https://openalex.org/S166990724","display_name":"IEICE Transactions on Fundamentals of Electronics Communications and Computer Sciences","issn_l":"0916-8508","issn":["0916-8508","1745-1337"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G174787991","display_name":null,"funder_award_id":"62001215","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6249807887","display_name":null,"funder_award_id":"2020YFC2004003","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387298048.pdf"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W2103235956","https://openalex.org/W2884585870","https://openalex.org/W2900315145","https://openalex.org/W3012504141","https://openalex.org/W3015530480","https://openalex.org/W3027732850","https://openalex.org/W3097327166","https://openalex.org/W3127323627","https://openalex.org/W3162320900"],"related_works":["https://openalex.org/W3109219622","https://openalex.org/W2776062836","https://openalex.org/W4385282352","https://openalex.org/W3199841937","https://openalex.org/W2396592261","https://openalex.org/W1965488317","https://openalex.org/W2138735934","https://openalex.org/W3132521424","https://openalex.org/W266630859","https://openalex.org/W2766891017"],"abstract_inverted_index":{"Convolutional":[0],"neural":[1,52],"network":[2,53],"(CNN)":[3],"is":[4,18,28],"widely":[5],"used":[6],"in":[7,39],"acoustic":[8],"scene":[9],"classification":[10],"(ASC)":[11],"tasks.":[12],"In":[13,44],"most":[14],"cases,":[15],"local":[16],"convolution":[17,42],"utilized":[19],"to":[20,30,74,94,129,146,158],"gather":[21],"time-frequency":[22,111],"information":[23,112,124],"between":[24,36,99,106],"spectrum":[25],"nodes.":[26],"It":[27],"challenging":[29],"adequately":[31],"express":[32],"the":[33,65,76,82,96,110,116,130,138,141,144,148,152,159,166],"non-local":[34,123],"link":[35],"frequency":[37,101],"domains":[38],"a":[40,49],"finite":[41],"region.":[43],"this":[45],"paper,":[46],"we":[47,86],"propose":[48],"dual-path":[50],"convolutional":[51],"based":[54],"on":[55],"band":[56,90],"interaction":[57,91],"block":[58],"(DCNN-bi)":[59],"for":[60],"ASC,":[61],"with":[62,118],"mel-spectrogram":[63],"as":[64],"model's":[66],"input.":[67],"We":[68],"build":[69],"two":[70,107,114],"parallel":[71],"CNN":[72,153,167],"paths":[73],"learn":[75],"high-frequency":[77],"and":[78,125,162,173],"low-frequency":[79],"components":[80],"of":[81,140,151,171],"input":[83],"feature.":[84],"Additionally,":[85],"have":[87],"created":[88],"three":[89,119],"blocks":[92],"(bi-blocks)":[93],"explore":[95],"pertinent":[97],"nodes":[98],"various":[100],"bands,":[102],"which":[103],"are":[104],"connected":[105],"paths.":[108,132],"Combining":[109],"from":[113],"paths,":[115],"bi-blocks":[117],"distinct":[120],"designs":[121],"acquire":[122],"send":[126],"it":[127],"back":[128],"respective":[131],"The":[133],"experimental":[134],"results":[135],"indicate":[136],"that":[137],"utilization":[139],"bi-block":[142],"has":[143],"potential":[145],"improve":[147],"initial":[149],"performance":[150,169],"substantially.":[154],"Specifically,":[155],"when":[156],"applied":[157],"DCASE":[160,163],"2018":[161],"2020":[164],"datasets,":[165],"exhibited":[168],"improvements":[170],"1.79%":[172],"3.06%,":[174],"respectively.":[175]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}