{"id":"https://openalex.org/W4390463261","doi":"https://doi.org/10.1587/transinf.2023edp7107","title":"Research on Lightweight Acoustic Scene Perception Method Based on Drunkard Methodology","display_name":"Research on Lightweight Acoustic Scene Perception Method Based on Drunkard Methodology","publication_year":2023,"publication_date":"2023-12-31","ids":{"openalex":"https://openalex.org/W4390463261","doi":"https://doi.org/10.1587/transinf.2023edp7107"},"language":"en","primary_location":{"id":"doi:10.1587/transinf.2023edp7107","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1587/transinf.2023edp7107","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E107.D/1/E107.D_2023EDP7107/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"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 Information and Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.jstage.jst.go.jp/article/transinf/E107.D/1/E107.D_2023EDP7107/_pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101507963","display_name":"Wenkai Liu","orcid":"https://orcid.org/0000-0002-6694-3306"},"institutions":[{"id":"https://openalex.org/I1456306","display_name":"North China University of Technology","ror":"https://ror.org/01nky7652","country_code":"CN","type":"education","lineage":["https://openalex.org/I1456306"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wenkai LIU","raw_affiliation_strings":["North China University of Technology"],"affiliations":[{"raw_affiliation_string":"North China University of Technology","institution_ids":["https://openalex.org/I1456306"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102007813","display_name":"Lin Zhang","orcid":"https://orcid.org/0000-0002-6903-5194"},"institutions":[{"id":"https://openalex.org/I1456306","display_name":"North China University of Technology","ror":"https://ror.org/01nky7652","country_code":"CN","type":"education","lineage":["https://openalex.org/I1456306"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin ZHANG","raw_affiliation_strings":["North China University of Technology"],"affiliations":[{"raw_affiliation_string":"North China University of Technology","institution_ids":["https://openalex.org/I1456306"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020141456","display_name":"Menglong Wu","orcid":"https://orcid.org/0000-0003-1818-9019"},"institutions":[{"id":"https://openalex.org/I1456306","display_name":"North China University of Technology","ror":"https://ror.org/01nky7652","country_code":"CN","type":"education","lineage":["https://openalex.org/I1456306"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Menglong WU","raw_affiliation_strings":["North China University of Technology"],"affiliations":[{"raw_affiliation_string":"North China University of Technology","institution_ids":["https://openalex.org/I1456306"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015281297","display_name":"Xichang Cai","orcid":"https://orcid.org/0000-0003-1333-8812"},"institutions":[{"id":"https://openalex.org/I1456306","display_name":"North China University of Technology","ror":"https://ror.org/01nky7652","country_code":"CN","type":"education","lineage":["https://openalex.org/I1456306"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xichang CAI","raw_affiliation_strings":["North China University of Technology"],"affiliations":[{"raw_affiliation_string":"North China University of Technology","institution_ids":["https://openalex.org/I1456306"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070754368","display_name":"Hongxia Dong","orcid":"https://orcid.org/0000-0002-8443-2155"},"institutions":[{"id":"https://openalex.org/I1456306","display_name":"North China University of Technology","ror":"https://ror.org/01nky7652","country_code":"CN","type":"education","lineage":["https://openalex.org/I1456306"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongxia DONG","raw_affiliation_strings":["North China University of Technology"],"affiliations":[{"raw_affiliation_string":"North China University of Technology","institution_ids":["https://openalex.org/I1456306"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101507963"],"corresponding_institution_ids":["https://openalex.org/I1456306"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19584403,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"E107.D","issue":"1","first_page":"83","last_page":"92"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9757999777793884,"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":0.9757999777793884,"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":0.813209593296051},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.6369291543960571},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.630933403968811},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.6231831312179565},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.5762732625007629},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5735669136047363},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5727365612983704},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49805426597595215},{"id":"https://openalex.org/keywords/iterative-and-incremental-development","display_name":"Iterative and incremental development","score":0.4425085186958313},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4248395562171936},{"id":"https://openalex.org/keywords/homogeneous","display_name":"Homogeneous","score":0.42142254114151},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35238221287727356},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09717759490013123}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.813209593296051},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.6369291543960571},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.630933403968811},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.6231831312179565},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.5762732625007629},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5735669136047363},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5727365612983704},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49805426597595215},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.4425085186958313},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4248395562171936},{"id":"https://openalex.org/C66882249","wikidata":"https://www.wikidata.org/wiki/Q169336","display_name":"Homogeneous","level":2,"score":0.42142254114151},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35238221287727356},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09717759490013123},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","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},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1587/transinf.2023edp7107","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1587/transinf.2023edp7107","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E107.D/1/E107.D_2023EDP7107/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"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 Information and Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1587/transinf.2023edp7107","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1587/transinf.2023edp7107","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E107.D/1/E107.D_2023EDP7107/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"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 Information and Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.6200000047683716,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4390463261.pdf"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W1821462560","https://openalex.org/W2194775991","https://openalex.org/W2752782242","https://openalex.org/W2765407302","https://openalex.org/W2883780447","https://openalex.org/W2883935097","https://openalex.org/W2928165649","https://openalex.org/W2936774411","https://openalex.org/W2963163009","https://openalex.org/W2982083293","https://openalex.org/W3004543888","https://openalex.org/W3035414587","https://openalex.org/W3177052299","https://openalex.org/W3177390112","https://openalex.org/W4210634873","https://openalex.org/W4220721682","https://openalex.org/W4281633835","https://openalex.org/W4282044900","https://openalex.org/W4283726207","https://openalex.org/W4291146221","https://openalex.org/W4295723153","https://openalex.org/W4310416255","https://openalex.org/W4310609408","https://openalex.org/W4310845421","https://openalex.org/W4313144836"],"related_works":["https://openalex.org/W2366107444","https://openalex.org/W4388145910","https://openalex.org/W1976205134","https://openalex.org/W2381570729","https://openalex.org/W4248336175","https://openalex.org/W3009369890","https://openalex.org/W2031260042","https://openalex.org/W2391445434","https://openalex.org/W4312490297","https://openalex.org/W2062212388"],"abstract_inverted_index":{"The":[0,81,136],"goal":[1],"of":[2,12,58,66,99,111,165,192,209,238],"Acoustic":[3],"Scene":[4],"Classification":[5],"(ASC)":[6],"is":[7,30,224,231],"to":[8,35,107,169,173,226],"simulate":[9,108],"human":[10],"analysis":[11],"the":[13,55,63,78,96,109,116,130,166,170,176,189,207,219,222,229,236],"surrounding":[14],"environment":[15],"and":[16,32,62,69,104,115,145,162,179,183,203,212,228,241],"make":[17],"accurate":[18],"decisions":[19],"promptly.":[20],"Extracting":[21],"useful":[22],"information":[23,100,153],"from":[24],"audio":[25],"signals":[26],"in":[27,38,43,60,118],"real-world":[28],"scenarios":[29],"challenging":[31],"can":[33,146],"lead":[34],"suboptimal":[36],"performance":[37],"acoustic":[39],"scene":[40],"classification,":[41],"especially":[42],"environments":[44],"with":[45],"relatively":[46],"homogeneous":[47],"backgrounds.":[48],"To":[49],"address":[50],"this":[51],"problem,":[52],"we":[53],"model":[54,74,127,137,168,172],"sobering-up":[56,177],"process":[57,110,178],"\u201cdrunkards\u201d":[59],"real-life":[61],"guiding":[64,161],"behavior":[65],"normal":[67,131],"people,":[68,106],"construct":[70],"a":[71,89,124,139,160],"high-precision":[72],"lightweight":[73,125],"implementation":[75],"methodology":[76],"called":[77],"\u201cdrunkard":[79],"methodology\u201d.":[80],"core":[82],"idea":[83],"includes":[84],"three":[85],"parts:":[86],"(1)":[87],"designing":[88],"special":[90],"feature":[91,119,149],"transformation":[92],"module":[93,164],"based":[94],"on":[95,188],"different":[97,156],"mechanisms":[98],"perception":[101,120,133],"between":[102],"drunkards":[103],"ordinary":[105],"gradually":[112],"sobering":[113],"up":[114,175],"changes":[117],"ability;":[121],"(2)":[122],"studying":[123],"\u201cdrunken\u201d":[126,171],"that":[128,196],"matches":[129],"model's":[132],"processing":[134],"process.":[135],"uses":[138],"multi-scale":[140],"class":[141],"residual":[142],"block":[143],"structure":[144],"obtain":[147],"finer":[148],"representations":[150],"by":[151,233],"fusing":[152],"extracted":[154],"at":[155],"scales;":[157],"(3)":[158],"introducing":[159],"fusion":[163],"conventional":[167],"speed":[174],"achieve":[180],"iterative":[181],"optimization":[182],"accuracy":[184,202,223],"improvement.":[185],"Evaluation":[186],"results":[187],"official":[190],"dataset":[191],"DCASE2022":[193],"Task1":[194],"demonstrate":[195],"our":[197],"baseline":[198],"system":[199],"achieves":[200],"40.4%":[201],"2.284":[204],"loss":[205,230],"under":[206,235],"condition":[208,237],"442.67K":[210],"parameters":[211,240],"19.40M":[213],"MAC":[214],"(multiply-accumulate":[215],"operations).":[216],"After":[217],"adopting":[218],"\u201cdrunkard\u201d":[220],"mechanism,":[221],"improved":[225],"45.2%,":[227],"reduced":[232],"0.634":[234],"551.89K":[239],"23.6M":[242],"MAC.":[243]},"counts_by_year":[],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}
