{"id":"https://openalex.org/W4414169586","doi":"https://doi.org/10.1109/avss65446.2025.11149784","title":"Modelling Spatio-Temporal Dynamics by Graph Attention Network for Distributed Multi-Microphone Sound Event Classification","display_name":"Modelling Spatio-Temporal Dynamics by Graph Attention Network for Distributed Multi-Microphone Sound Event Classification","publication_year":2025,"publication_date":"2025-08-11","ids":{"openalex":"https://openalex.org/W4414169586","doi":"https://doi.org/10.1109/avss65446.2025.11149784"},"language":"en","primary_location":{"id":"doi:10.1109/avss65446.2025.11149784","is_oa":false,"landing_page_url":"https://doi.org/10.1109/avss65446.2025.11149784","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Advanced Visual and Signal-Based Systems (AVSS)","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/A5007962043","display_name":"Vijay John","orcid":"https://orcid.org/0000-0002-9553-0906"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Vijay John","raw_affiliation_strings":["RIKEN,Guardian Robot Project,Kyoto,Japan"],"affiliations":[{"raw_affiliation_string":"RIKEN,Guardian Robot Project,Kyoto,Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027960360","display_name":"Yasutomo Kawanishi","orcid":"https://orcid.org/0000-0002-3799-4550"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yasutomo Kawanishi","raw_affiliation_strings":["RIKEN,Guardian Robot Project,Kyoto,Japan"],"affiliations":[{"raw_affiliation_string":"RIKEN,Guardian Robot Project,Kyoto,Japan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5007962043"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.32052695,"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":1.0,"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":1.0,"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":0.9980000257492065,"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":0.9958999752998352,"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/graph","display_name":"Graph","score":0.6650999784469604},{"id":"https://openalex.org/keywords/attention-network","display_name":"Attention network","score":0.5271999835968018},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.4648999869823456},{"id":"https://openalex.org/keywords/power-graph-analysis","display_name":"Power graph analysis","score":0.39419999718666077},{"id":"https://openalex.org/keywords/graph-theory","display_name":"Graph theory","score":0.3345000147819519},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.30730000138282776}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7422000169754028},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.6650999784469604},{"id":"https://openalex.org/C2993807640","wikidata":"https://www.wikidata.org/wiki/Q103709453","display_name":"Attention network","level":2,"score":0.5271999835968018},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.4648999869823456},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4431999921798706},{"id":"https://openalex.org/C106937863","wikidata":"https://www.wikidata.org/wiki/Q7236518","display_name":"Power graph analysis","level":3,"score":0.39419999718666077},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37700000405311584},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3537999987602234},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.3345000147819519},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.30730000138282776},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30559998750686646},{"id":"https://openalex.org/C32946077","wikidata":"https://www.wikidata.org/wiki/Q618079","display_name":"Network analysis","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C34947359","wikidata":"https://www.wikidata.org/wiki/Q665189","display_name":"Complex network","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.25440001487731934}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/avss65446.2025.11149784","is_oa":false,"landing_page_url":"https://doi.org/10.1109/avss65446.2025.11149784","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Advanced Visual and Signal-Based Systems (AVSS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1501987291","https://openalex.org/W2903659352","https://openalex.org/W2996295914","https://openalex.org/W3160207687","https://openalex.org/W3161798961","https://openalex.org/W3197097128","https://openalex.org/W4221155627","https://openalex.org/W4393399596","https://openalex.org/W4400811112","https://openalex.org/W4401476348","https://openalex.org/W4403345597","https://openalex.org/W4403590327","https://openalex.org/W4403709550","https://openalex.org/W4404967341","https://openalex.org/W4408354509"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"a":[3,64,86,101,116],"novel":[4],"distributed":[5,23],"multi-microphone":[6,57,76],"sound":[7],"event":[8,130,150],"classification":[9,131,151],"framework":[10,65,79,143],"that":[11,140],"uses":[12],"graph":[13,69,84,88,105,117,125],"attention":[14,70,118],"networks":[15],"to":[16,72,94,110],"model":[17,73],"spatial":[18,51,104],"and":[19,45,52,97,100],"temporal":[20,53],"relationships":[21,54],"between":[22],"multi-microphones.":[24],"Existing":[25],"methods":[26,147],"utilize":[27],"naive":[28],"aggregation":[29,120],"approaches":[30],"like":[31],"concatenation,":[32],"averaging,":[33],"or":[34],"maximum":[35],"operations":[36],"for":[37,148],"multiple":[38],"sensor":[39],"inputs":[40],"resulting":[41,127],"in":[42,47,55,128],"information":[43],"loss":[44],"limitations":[46],"capturing":[48],"the":[49,56,68,74,124,136,149],"complex":[50,75],"sequence.":[58],"To":[59],"address":[60],"this,":[61],"we":[62],"propose":[63],"based":[66,81],"on":[67,82,135],"network":[71],"relationship.":[77],"Our":[78],"is":[80,91,108],"two":[83],"structures:":[85],"spatio-temporal":[87],"(STG),":[89],"which":[90,107],"algorithmically":[92],"modeled":[93],"capture":[95,111],"inter-microphone":[96],"inter-frame":[98],"relationships,":[99],"learnable":[102],"fully-connected":[103],"(FCSG),":[106],"designed":[109],"complementary":[112],"details.":[113],"Utilizing":[114],"them,":[115],"network-based":[119],"module":[121],"effectively":[122],"updates":[123],"nodes":[126],"improved":[129],"accuracy.":[132],"Experimental":[133],"results":[134],"MM-Office":[137],"dataset":[138],"demonstrate":[139],"our":[141],"proposed":[142],"significantly":[144],"outperforms":[145],"baseline":[146],"task.":[152]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}