{"id":"https://openalex.org/W4416799973","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249095","title":"Training Acoustic Scene Classification Models Robust to Asynchrony in Distributed Microphone Arrays","display_name":"Training Acoustic Scene Classification Models Robust to Asynchrony in Distributed Microphone Arrays","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416799973","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249095"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249095","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249095","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":"https://openalex.org/A5050509317","display_name":"Takao Kawamura","orcid":"https://orcid.org/0009-0005-3935-2809"},"institutions":[{"id":"https://openalex.org/I69740276","display_name":"Tokyo Metropolitan University","ror":"https://ror.org/00ws30h19","country_code":"JP","type":"education","lineage":["https://openalex.org/I69740276"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takao Kawamura","raw_affiliation_strings":["Tokyo Metropolitan University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Metropolitan University,Japan","institution_ids":["https://openalex.org/I69740276"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056281759","display_name":"Nobutaka Ono","orcid":"https://orcid.org/0000-0003-4242-2773"},"institutions":[{"id":"https://openalex.org/I69740276","display_name":"Tokyo Metropolitan University","ror":"https://ror.org/00ws30h19","country_code":"JP","type":"education","lineage":["https://openalex.org/I69740276"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nobutaka Ono","raw_affiliation_strings":["Tokyo Metropolitan University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Metropolitan University,Japan","institution_ids":["https://openalex.org/I69740276"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I69740276"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.40562574,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.8080000281333923,"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":0.8080000281333923,"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":0.12460000067949295,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.017100000753998756,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/asynchrony","display_name":"Asynchrony (computer programming)","score":0.8385999798774719},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.8131999969482422},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.7633000016212463},{"id":"https://openalex.org/keywords/spatial-analysis","display_name":"Spatial analysis","score":0.5328999757766724},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4537999927997589},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.42570000886917114},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.3723999857902527},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36890000104904175}],"concepts":[{"id":"https://openalex.org/C2779019669","wikidata":"https://www.wikidata.org/wiki/Q25203946","display_name":"Asynchrony (computer programming)","level":3,"score":0.8385999798774719},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.8131999969482422},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7735000252723694},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.7633000016212463},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.5328999757766724},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47609999775886536},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4717000126838684},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4537999927997589},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.42570000886917114},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.3723999857902527},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36890000104904175},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35929998755455017},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.31839999556541443},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.31630000472068787},{"id":"https://openalex.org/C177860922","wikidata":"https://www.wikidata.org/wiki/Q788608","display_name":"Decorrelation","level":2,"score":0.2976999878883362},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.2775000035762787},{"id":"https://openalex.org/C194226119","wikidata":"https://www.wikidata.org/wiki/Q161779","display_name":"Spatial reference system","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.2605000138282776},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.25270000100135803},{"id":"https://openalex.org/C2779679103","wikidata":"https://www.wikidata.org/wiki/Q5251805","display_name":"Degradation (telecommunications)","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249095","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249095","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":[{"id":"https://openalex.org/G6375115404","display_name":null,"funder_award_id":"JP24KJ1866","funder_id":"https://openalex.org/F4320320212","funder_display_name":"Japan Society for the Promotion of Science London"}],"funders":[{"id":"https://openalex.org/F4320320212","display_name":"Japan Society for the Promotion of Science London","ror":"https://ror.org/02m7axw05"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W153185079","https://openalex.org/W2046317813","https://openalex.org/W2092463830","https://openalex.org/W2160335114","https://openalex.org/W2160860215","https://openalex.org/W2166595512","https://openalex.org/W2618657287","https://openalex.org/W2747805921","https://openalex.org/W2906655028","https://openalex.org/W2936774411","https://openalex.org/W2942551338","https://openalex.org/W2951942899","https://openalex.org/W3005741390","https://openalex.org/W3006885863","https://openalex.org/W3109048247","https://openalex.org/W3154119858","https://openalex.org/W3160061063","https://openalex.org/W3208412799","https://openalex.org/W4280542824","https://openalex.org/W4372341277","https://openalex.org/W4387244556","https://openalex.org/W4388820849","https://openalex.org/W4392114354","https://openalex.org/W4392903751","https://openalex.org/W4402111589","https://openalex.org/W4405661978"],"related_works":[],"abstract_inverted_index":{"In":[0,69],"this":[1,50,121],"study,":[2],"we":[3,73,95,123],"explore":[4],"whether":[5,111],"phase-based":[6,79,101,143],"spatial":[7,26,80,107,144],"features":[8,81,102],"can":[9,24],"still":[10,104],"provide":[11],"informative":[12],"cues":[13],"for":[14,42],"acoustic":[15,43],"scene":[16,44],"classification":[17],"under":[18,99],"asynchronous":[19,92,131,170],"conditions.":[20,171],"Distributed":[21],"microphone":[22,37],"arrays":[23],"capture":[25],"information":[27,51],"over":[28],"a":[29,112,125],"large":[30],"area,":[31],"such":[32,109],"as":[33,110],"time":[34,57],"differences":[35],"between":[36],"recordings,":[38],"which":[39],"are":[40,155],"useful":[41,106],"classification.":[45],"However,":[46],"in":[47],"real-world":[48],"applications,":[49],"becomes":[52],"unreliable":[53],"due":[54],"to":[55,137,151,157],"sampling":[56],"offsets":[58],"(STOs)":[59],"caused":[60],"by":[61,133],"unsynchronized":[62],"recording":[63],"start":[64],"times":[65],"or":[66,117],"clock":[67],"drift.":[68],"our":[70,163],"previous":[71],"work,":[72],"showed":[74],"that":[75,97,129,154,162],"models":[76],"trained":[77],"on":[78,91],"using":[82],"synchronized":[83,138],"data":[84,126,139],"suffer":[85],"significant":[86],"performance":[87,166],"degradation":[88,167],"when":[89],"tested":[90],"recordings.":[93],"Nevertheless,":[94],"hypothesize":[96],"even":[98],"STOs,":[100],"may":[103],"contain":[105],"cues,":[108],"sound":[113],"source":[114],"is":[115],"moving":[116],"stationary.":[118],"To":[119],"examine":[120],"hypothesis,":[122],"apply":[124],"augmentation":[127],"strategy":[128],"simulates":[130],"conditions":[132],"introducing":[134],"circular":[135],"shifts":[136],"and":[140],"then":[141],"compute":[142],"features.":[145],"This":[146],"approach":[147],"allows":[148],"the":[149],"model":[150],"learn":[152],"representations":[153],"robust":[156],"STOs.":[158],"Experimental":[159],"results":[160],"demonstrate":[161],"method":[164],"mitigates":[165],"across":[168],"various":[169]},"counts_by_year":[],"updated_date":"2026-07-05T07:55:05.734416","created_date":"2025-11-28T00:00:00"}