{"id":"https://openalex.org/W7107853917","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249206","title":"ASCMamba: Multimodal Time-Frequency Mamba for Acoustic Scene Classification","display_name":"ASCMamba: Multimodal Time-Frequency Mamba for Acoustic Scene Classification","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W7107853917","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249206"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249206","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249206","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Bochao Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bochao Sun","raw_affiliation_strings":["School of Marine Science and Technology, Northwestern Polytechnical University,Xi'an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Marine Science and Technology, Northwestern Polytechnical University,Xi'an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Dong Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Wang","raw_affiliation_strings":["School of Automation, Northwestern Polytechnical University,Xi'an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation, Northwestern Polytechnical University,Xi'an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhanlong Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhanlong Yang","raw_affiliation_strings":["School of Marine Science and Technology, Northwestern Polytechnical University,Xi'an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Marine Science and Technology, Northwestern Polytechnical University,Xi'an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jun Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Yang","raw_affiliation_strings":["School of Automation, Northwestern Polytechnical University,Xi'an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation, Northwestern Polytechnical University,Xi'an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":null,"display_name":"Han Yin","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Han Yin","raw_affiliation_strings":["School of Electrical Engineering, KAIST,Daejeon,Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, KAIST,Daejeon,Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.541353,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"182","last_page":"187"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9563000202178955,"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":0.9563000202178955,"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":0.019500000402331352,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.00570000009611249,"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/task","display_name":"Task (project management)","score":0.701200008392334},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4611000120639801},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.3921000063419342},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.38920000195503235},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.3671000003814697},{"id":"https://openalex.org/keywords/multimodal-interaction","display_name":"Multimodal interaction","score":0.33390000462532043}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7656999826431274},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.701200008392334},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5048999786376953},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.489300012588501},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4611000120639801},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.3921000063419342},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.38920000195503235},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3671000003814697},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.33390000462532043},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.328900009393692},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.32839998602867126},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.28459998965263367},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.28380000591278076},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.25609999895095825}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249206","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249206","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2103235956","https://openalex.org/W2191779130","https://openalex.org/W2964121744","https://openalex.org/W3097327166","https://openalex.org/W4312097006","https://openalex.org/W4312765536","https://openalex.org/W4385245566","https://openalex.org/W4402170843","https://openalex.org/W4403844121","https://openalex.org/W4408353947","https://openalex.org/W4410536260"],"related_works":[],"abstract_inverted_index":{"Acoustic":[0],"Scene":[1],"Classification":[2],"(ASC)":[3],"is":[4,64],"a":[5,36,93,116,127,147,169],"fundamental":[6],"problem":[7],"in":[8,83],"computational":[9],"audition,":[10],"which":[11,97],"seeks":[12],"to":[13,118,151],"classify":[14],"environments":[15],"based":[16],"on":[17,47],"the":[18,23,27,33,59,62,67,80,84,159,164,174],"distinctive":[19],"acoustic":[20,105],"features.":[21],"In":[22,71,143],"ASC":[24,29,38,42,81,86],"task":[25,82],"of":[26,69],"APSIPA":[28,85],"2025":[30,87],"Grand":[31,88],"Challenge,":[32],"organizers":[34],"introduce":[35],"multimodal":[37,94,110],"task.":[39],"Unlike":[40],"traditional":[41],"systems":[43],"that":[44,131,158],"rely":[45],"solely":[46],"audio":[48,63,99],"inputs,":[49,57],"this":[50,72],"challenge":[51],"provides":[52],"additional":[53],"textual":[54,101],"information":[55,102],"as":[56],"including":[58],"location":[60],"where":[61],"recorded":[65],"and":[66,100,108,135,167,178],"time":[68],"recording.":[70],"paper,":[73],"we":[74,91,145],"present":[75,146],"our":[76],"proposed":[77,113,160],"system":[78,161],"for":[79,103],"Challenge.":[89],"Specifically,":[90],"propose":[92],"network,":[95],"ASCMamba,":[96],"integrates":[98],"fine-grained":[104],"scene":[106],"understanding":[107],"effective":[109],"ASC.":[111],"The":[112],"ASCMamba":[114],"employs":[115],"DenseEncoder":[117],"extract":[119],"hierarchical":[120],"spectral":[121],"features":[122],"from":[123],"spectrograms,":[124],"followed":[125],"by":[126],"dual-path":[128],"Mamba":[129],"blocks":[130],"capture":[132],"long-range":[133],"temporal":[134],"frequency":[136],"dependencies":[137],"using":[138],"Mamba-based":[139],"state":[140],"space":[141],"models.":[142],"addition,":[144],"two-step":[148],"pseudo-labeling":[149],"mechanism":[150],"generate":[152],"more":[153],"reliable":[154],"pseudo-labels.":[155],"Results":[156],"show":[157],"outperforms":[162],"all":[163],"participating":[165],"teams":[166],"achieves":[168],"6.2":[170],"%":[171],"improvement":[172],"over":[173],"baseline.":[175],"Code,":[176],"model":[177],"pre-trained":[179],"checkpoints":[180],"are":[181],"available":[182],"at":[183],"https://github.com/S-Orion/ASCMamba.git":[184]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-28T00:00:00"}