{"id":"https://openalex.org/W4327521077","doi":"https://doi.org/10.1145/3573428.3573633","title":"Multi-Feature Convergence Network for Acoustic Scene Classification","display_name":"Multi-Feature Convergence Network for Acoustic Scene Classification","publication_year":2022,"publication_date":"2022-10-21","ids":{"openalex":"https://openalex.org/W4327521077","doi":"https://doi.org/10.1145/3573428.3573633"},"language":"en","primary_location":{"id":"doi:10.1145/3573428.3573633","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3573428.3573633","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 6th International Conference on Electronic Information Technology and Computer Engineering","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/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":true,"raw_author_name":"Menglong Wu","raw_affiliation_strings":["North China University of Technology, China"],"affiliations":[{"raw_affiliation_string":"North China University of Technology, China","institution_ids":["https://openalex.org/I1456306"]}]},{"author_position":"middle","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, China"],"affiliations":[{"raw_affiliation_string":"North China University of Technology, China","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, China"],"affiliations":[{"raw_affiliation_string":"North China University of Technology, China","institution_ids":["https://openalex.org/I1456306"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062334502","display_name":"Ziling Qiao","orcid":"https://orcid.org/0000-0001-7130-1386"},"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":"Ziling Qiao","raw_affiliation_strings":["North China University of Technology, China"],"affiliations":[{"raw_affiliation_string":"North China University of Technology, China","institution_ids":["https://openalex.org/I1456306"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039574085","display_name":"Cuizhu QIN","orcid":"https://orcid.org/0000-0003-3522-6619"},"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":"Cuizhu Qin","raw_affiliation_strings":["North China University of Technology, China"],"affiliations":[{"raw_affiliation_string":"North China University of Technology, China","institution_ids":["https://openalex.org/I1456306"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114406799","display_name":"Lin Zhang","orcid":null},"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, China"],"affiliations":[{"raw_affiliation_string":"North China University of Technology, China","institution_ids":["https://openalex.org/I1456306"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5020141456"],"corresponding_institution_ids":["https://openalex.org/I1456306"],"apc_list":null,"apc_paid":null,"fwci":0.1486,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.44631721,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1142","last_page":"1145"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.982200026512146,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/spectrogram","display_name":"Spectrogram","score":0.9019785523414612},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6701825857162476},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.6655945777893066},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6563470959663391},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6337376832962036},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6203314661979675},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5658746957778931},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.45595717430114746},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.42852041125297546},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.41246891021728516},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4092143476009369},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.18381556868553162},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07180166244506836}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.9019785523414612},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6701825857162476},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.6655945777893066},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6563470959663391},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6337376832962036},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6203314661979675},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5658746957778931},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.45595717430114746},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.42852041125297546},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41246891021728516},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4092143476009369},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.18381556868553162},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07180166244506836},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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:10.1145/3573428.3573633","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3573428.3573633","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 6th International Conference on Electronic Information Technology and Computer Engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2076608692","https://openalex.org/W2939574508","https://openalex.org/W3017925328","https://openalex.org/W3097327166","https://openalex.org/W3201373735","https://openalex.org/W6737496325"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2088854863","https://openalex.org/W2011227383","https://openalex.org/W1976719989","https://openalex.org/W2942893872","https://openalex.org/W2065606036","https://openalex.org/W3179495260","https://openalex.org/W3127543252","https://openalex.org/W2972212393"],"abstract_inverted_index":{"This":[0],"paper":[1,208],"investigates":[2],"a":[3,53,108,141,163],"multi-feature":[4],"convergence":[5],"network":[6,16,117,122,194],"for":[7],"acoustic":[8],"scene":[9,179],"classification":[10,36,80,180,186,189],"(ASC).":[11],"A":[12],"series":[13],"of":[14,21,42,66,72,191,219],"neural":[15],"models":[17,150],"designed":[18],"with":[19,101],"features":[20],"the":[22,31,39,43,49,64,69,73,79,86,99,102,113,116,120,128,133,148,153,158,169,177,183,202,213,216],"Log":[23,74],"Mel":[24],"spectrogram,":[25],"Deltas,":[26],"and":[27,77,93,140,175,209],"Delta-Deltas":[28],"superimposed":[29,97],"on":[30,98,147,168,215],"channel":[32,100],"have":[33],"achieved":[34],"good":[35],"results.":[37],"However,":[38],"low-frequency":[40,70],"part":[41,71],"speech":[44],"spectrogram":[45,90],"feature":[46,76,95,105,110],"extracted":[47],"from":[48,132],"audio":[50],"signal":[51],"has":[52],"mosaic":[54],"shape":[55],"due":[56,156],"to":[57,63,106,115,136,157],"its":[58],"low":[59],"resolution,":[60],"which":[61,197],"leads":[62],"loss":[65],"information":[67],"in":[68,206],"Mel-Deltas-DeltaDeltas":[75,104],"reduces":[78],"accuracy.":[81],"To":[82],"solve":[83],"this":[84,94,207],"problem,":[85],"constant":[87],"Q-transform":[88],"(CQT)":[89],"is":[91,96,124,145,165,198],"introduced":[92],"log":[103],"form":[107],"4-channel":[109],"spectrum":[111],"as":[112],"input":[114],"model.":[118],"Moreover,":[119],"proposed":[121,193],"model":[123],"deepened":[125],"by":[126,181],"increasing":[127],"8":[129],"residual":[130,138],"blocks":[131,139],"baseline":[134,203,214],"system":[135,204],"10":[137],"snapshot":[142],"integration":[143],"operation":[144],"performed":[146],"various":[149],"saved":[151],"during":[152],"training":[154],"process":[155],"complementary":[159],"information.":[160],"And":[161],"then,":[162],"3-classifier":[164],"added":[166],"based":[167],"ASC's":[170],"primarily":[171],"categorized":[172],"scenes'":[173],"10-classifier":[174],"chooses":[176],"final":[178],"combining":[182],"3\u201310":[184],"two-stage":[185],"scores.":[187],"The":[188],"accuracy":[190],"our":[192],"reached":[195],"77.4%,":[196],"5.1%":[199],"higher":[200,211],"than":[201,212],"set":[205],"26%":[210],"official":[217],"website":[218],"DCASE":[220],"2020.":[221]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}