{"id":"https://openalex.org/W4416799763","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249027","title":"A Semi-Supervised Acoustic Scene Classification Network Based on Multi-Modal Information Fusion","display_name":"A Semi-Supervised Acoustic Scene Classification Network Based on Multi-Modal Information Fusion","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416799763","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249027"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249027","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249027","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://bura.brunel.ac.uk/bitstream/2438/33270/1/FullText.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101826259","display_name":"Ji-Su Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I66906201","display_name":"University of Yamanashi","ror":"https://ror.org/059x21724","country_code":"JP","type":"education","lineage":["https://openalex.org/I66906201"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Junkang Yang","raw_affiliation_strings":["Integrated Graduate School of Medicine, Engineering, and Agricultural Sciences, University of Yamanashi,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Integrated Graduate School of Medicine, Engineering, and Agricultural Sciences, University of Yamanashi,Japan","institution_ids":["https://openalex.org/I66906201"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087997088","display_name":"Hongqing Liu","orcid":"https://orcid.org/0000-0003-4839-1525"},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongqing Liu","raw_affiliation_strings":["Chongqing Key Lab of Mobile Communications Technology, Chongqing University of Posts and Telecommunications,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chongqing Key Lab of Mobile Communications Technology, Chongqing University of Posts and Telecommunications,China","institution_ids":["https://openalex.org/I10535382"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084126009","display_name":"Liming Shi","orcid":"https://orcid.org/0000-0003-4129-0668"},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liming Shi","raw_affiliation_strings":["School of Communications and Information Engineering, Chongqing University of Posts and Telecommunications,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Communications and Information Engineering, Chongqing University of Posts and Telecommunications,China","institution_ids":["https://openalex.org/I10535382"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087344550","display_name":"Lu Gan","orcid":"https://orcid.org/0000-0002-1811-1011"},"institutions":[{"id":"https://openalex.org/I59433898","display_name":"Brunel University of London","ror":"https://ror.org/00dn4t376","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I59433898"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Lu Gan","raw_affiliation_strings":["College of Engineering, Design and Physical Science, Brunel University,U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Engineering, Design and Physical Science, Brunel University,U.K","institution_ids":["https://openalex.org/I59433898"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014342555","display_name":"Hiromitsu Nishizaki","orcid":"https://orcid.org/0000-0002-7717-8312"},"institutions":[{"id":"https://openalex.org/I66906201","display_name":"University of Yamanashi","ror":"https://ror.org/059x21724","country_code":"JP","type":"education","lineage":["https://openalex.org/I66906201"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiromitsu Nishizaki","raw_affiliation_strings":["Integrated Graduate School of Medicine, Engineering, and Agricultural Sciences, University of Yamanashi,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Integrated Graduate School of Medicine, Engineering, and Agricultural Sciences, University of Yamanashi,Japan","institution_ids":["https://openalex.org/I66906201"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070048885","display_name":"Chee Siang Leow","orcid":null},"institutions":[{"id":"https://openalex.org/I66906201","display_name":"University of Yamanashi","ror":"https://ror.org/059x21724","country_code":"JP","type":"education","lineage":["https://openalex.org/I66906201"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Chee Siang Leow","raw_affiliation_strings":["Integrated Graduate School of Medicine, Engineering, and Agricultural Sciences, University of Yamanashi,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Integrated Graduate School of Medicine, Engineering, and Agricultural Sciences, University of Yamanashi,Japan","institution_ids":["https://openalex.org/I66906201"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.40710353,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"177","last_page":"181"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9492999911308289,"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":0.9492999911308289,"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":0.007300000172108412,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.006000000052154064,"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/metadata","display_name":"Metadata","score":0.7639999985694885},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5630000233650208},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5511999726295471},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.4726000130176544},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4453999996185303},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.44359999895095825},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.4368000030517578},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3937000036239624}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.7639999985694885},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7486000061035156},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5781999826431274},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5630000233650208},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5511999726295471},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.4726000130176544},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4453999996185303},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.44359999895095825},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.4368000030517578},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3937000036239624},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.3873000144958496},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.3801000118255615},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3765999972820282},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3723999857902527},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3379000127315521},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2856000065803528},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.27959999442100525},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2793999910354614},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.275299996137619},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.275299996137619},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.2517000138759613}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249027","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249027","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"},{"id":"pmh:oai:bura.brunel.ac.uk:2438/33270","is_oa":true,"landing_page_url":"https://bura.brunel.ac.uk/handle/2438/33270","pdf_url":"http://bura.brunel.ac.uk/bitstream/2438/33270/1/FullText.pdf","source":{"id":"https://openalex.org/S4306401473","display_name":"Brunel University Research Archive (BURA) (Brunel University London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I59433898","host_organization_name":"Brunel University of London","host_organization_lineage":["https://openalex.org/I59433898"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"Conference Paper"}],"best_oa_location":{"id":"pmh:oai:bura.brunel.ac.uk:2438/33270","is_oa":true,"landing_page_url":"https://bura.brunel.ac.uk/handle/2438/33270","pdf_url":"http://bura.brunel.ac.uk/bitstream/2438/33270/1/FullText.pdf","source":{"id":"https://openalex.org/S4306401473","display_name":"Brunel University Research Archive (BURA) (Brunel University London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I59433898","host_organization_name":"Brunel University of London","host_organization_lineage":["https://openalex.org/I59433898"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"Conference Paper"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416799763.pdf","grobid_xml":"https://content.openalex.org/works/W4416799763.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W2132083787","https://openalex.org/W2936774411","https://openalex.org/W4297841833","https://openalex.org/W4312097006","https://openalex.org/W4365504037","https://openalex.org/W4387244556","https://openalex.org/W4401991020","https://openalex.org/W4406800337"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"our":[3,124,131],"semi-supervised":[4,81,128],"acoustic":[5,50],"scene":[6,51],"classification":[7],"(ASC)":[8],"framework":[9],"submitted":[10],"to":[11,47,107],"the":[12,109,121],"APSIPA":[13],"ASC":[14,24],"2025":[15],"Grand":[16],"Challenge,":[17],"which":[18],"focuses":[19],"on":[20,84,102,130],"city-":[21],"and":[22,45,90,95,98,127],"timeaware":[23],"under":[25],"limited":[26],"labeled":[27],"data.":[28,133],"Our":[29],"approach":[30],"leverages":[31],"a":[32,59,79],"multi-modal":[33,71],"network":[34],"architecture":[35],"that":[36],"fuses":[37],"audio":[38],"melspectrograms":[39],"with":[40,62,93,105],"spatiotemporal":[41],"metadata":[42],"(city":[43],"identity":[44],"timestamps)":[46],"capture":[48],"dynamic":[49],"variations":[52],"across":[53],"urban":[54],"environments.":[55],"The":[56],"model":[57],"employs":[58],"residual-based":[60],"CNN":[61],"attention":[63],"mechanisms":[64],"for":[65],"robust":[66],"feature":[67],"extraction,":[68],"enhanced":[69],"by":[70],"fusion.":[72],"To":[73],"address":[74],"label":[75],"scarcity,":[76],"we":[77],"adopt":[78],"staged":[80],"pipeline:":[82],"pre-training":[83],"TAU":[85],"Urban":[86],"Acoustic":[87],"Scenes":[88],"2020":[89],"CochlScene":[91],"datasets":[92],"specaugment":[94],"mixup":[96],"augmentations,":[97],"then":[99],"iterative":[100],"fine-tuning":[101],"challenge":[103],"data":[104],"pseudo-labeling":[106],"expand":[108],"training":[110],"set":[111],"was":[112],"conducted,":[113],"resulting":[114],"in":[115],"performance":[116],"improvement.":[117],"Experimental":[118],"results":[119],"demonstrate":[120],"efficacy":[122],"of":[123],"city/time-aware":[125],"design":[126],"strategies":[129],"validation":[132]},"counts_by_year":[],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-11-28T00:00:00"}