{"id":"https://openalex.org/W4387068368","doi":"https://doi.org/10.1109/lsp.2023.3319233","title":"Audio Event-Relational Graph Representation Learning for Acoustic Scene Classification","display_name":"Audio Event-Relational Graph Representation Learning for Acoustic Scene Classification","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4387068368","doi":"https://doi.org/10.1109/lsp.2023.3319233"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2023.3319233","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lsp.2023.3319233","pdf_url":"https://ieeexplore.ieee.org/ielx7/97/4358004/10264066.pdf","source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/97/4358004/10264066.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063248625","display_name":"Yuanbo Hou","orcid":"https://orcid.org/0000-0001-8469-5740"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":true,"raw_author_name":"Yuanbo Hou","raw_affiliation_strings":["WAVES Research Group, Ghent University, Ghent, Belgium"],"affiliations":[{"raw_affiliation_string":"WAVES Research Group, Ghent University, Ghent, Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053061988","display_name":"Siyang Song","orcid":"https://orcid.org/0000-0003-2339-5685"},"institutions":[{"id":"https://openalex.org/I153648349","display_name":"University of Leicester","ror":"https://ror.org/04h699437","country_code":"GB","type":"education","lineage":["https://openalex.org/I153648349"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Siyang Song","raw_affiliation_strings":["School of Computing and Mathematical Science, University of Leicester, Leicester, U.K"],"affiliations":[{"raw_affiliation_string":"School of Computing and Mathematical Science, University of Leicester, Leicester, U.K","institution_ids":["https://openalex.org/I153648349"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042248392","display_name":"Chuang Yu","orcid":"https://orcid.org/0000-0003-3185-3578"},"institutions":[{"id":"https://openalex.org/I2801237587","display_name":"London Centre for Nanotechnology","ror":"https://ror.org/04ptp8872","country_code":"GB","type":"facility","lineage":["https://openalex.org/I2801237587"]},{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Chuang Yu","raw_affiliation_strings":["UCL Interaction Centre, University College London, London, U.K"],"affiliations":[{"raw_affiliation_string":"UCL Interaction Centre, University College London, London, U.K","institution_ids":["https://openalex.org/I2801237587","https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100676721","display_name":"Wenwu Wang","orcid":"https://orcid.org/0000-0002-8393-5703"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wenwu Wang","raw_affiliation_strings":["Centre for Vision, Speech, and Signal Processing, University of Surrey, Guildford, U.K"],"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech, and Signal Processing, University of Surrey, Guildford, U.K","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069519911","display_name":"Dick Botteldooren","orcid":"https://orcid.org/0000-0002-7756-7238"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Dick Botteldooren","raw_affiliation_strings":["WAVES Research Group, Ghent University, Ghent, Belgium"],"affiliations":[{"raw_affiliation_string":"WAVES Research Group, Ghent University, Ghent, Belgium","institution_ids":["https://openalex.org/I32597200"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5063248625"],"corresponding_institution_ids":["https://openalex.org/I32597200"],"apc_list":null,"apc_paid":null,"fwci":1.9707,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.87448967,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"30","issue":null,"first_page":"1382","last_page":"1386"},"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":0.9930999875068665,"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":0.9864000082015991,"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/computer-science","display_name":"Computer science","score":0.7822469472885132},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5894588232040405},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5725159645080566},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5447240471839905},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5129053592681885},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4911038875579834},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4705486595630646},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.4627419114112854},{"id":"https://openalex.org/keywords/statistical-relational-learning","display_name":"Statistical relational learning","score":0.45598509907722473},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33717286586761475},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.32762524485588074},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.23491722345352173},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.17829042673110962},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.15051323175430298}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7822469472885132},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5894588232040405},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5725159645080566},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5447240471839905},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5129053592681885},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4911038875579834},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4705486595630646},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.4627419114112854},{"id":"https://openalex.org/C177877439","wikidata":"https://www.wikidata.org/wiki/Q7604413","display_name":"Statistical relational learning","level":3,"score":0.45598509907722473},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33717286586761475},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.32762524485588074},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.23491722345352173},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.17829042673110962},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.15051323175430298},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/lsp.2023.3319233","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lsp.2023.3319233","pdf_url":"https://ieeexplore.ieee.org/ielx7/97/4358004/10264066.pdf","source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2310.03889","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.03889","pdf_url":"https://arxiv.org/pdf/2310.03889","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:archive.ugent.be:01HHHD156KGAY2M9GW1K8CTP32","is_oa":true,"landing_page_url":"http://hdl.handle.net/1854/LU-01HHHD156KGAY2M9GW1K8CTP32","pdf_url":"https://biblio.ugent.be/publication/01HHHD156KGAY2M9GW1K8CTP32/file/01HHHDAFBSF56BBTQ8TPBJCTBC.pdf","source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"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":"ISSN: 1558-2361","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:eprints.ucl.ac.uk.OAI2:10179898","is_oa":true,"landing_page_url":"https://discovery.ucl.ac.uk/id/eprint/10179898/","pdf_url":"https://discovery.ucl.ac.uk/10179898/1/Audio_Event-Relational_Graph_Representation_Learning_for_Acoustic_Scene_Classification.pdf","source":{"id":"https://openalex.org/S4306400024","display_name":"UCL Discovery (University College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45129253","host_organization_name":"University College London","host_organization_lineage":["https://openalex.org/I45129253"],"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":"   IEEE Signal Processing Letters , 30    pp. 1382-1386.   (2023)      ","raw_type":"Article"}],"best_oa_location":{"id":"doi:10.1109/lsp.2023.3319233","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lsp.2023.3319233","pdf_url":"https://ieeexplore.ieee.org/ielx7/97/4358004/10264066.pdf","source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320327336","display_name":"Vlaamse regering","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387068368.pdf","grobid_xml":"https://content.openalex.org/works/W4387068368.grobid-xml"},"referenced_works_count":54,"referenced_works":["https://openalex.org/W1233529392","https://openalex.org/W1514872063","https://openalex.org/W2086384421","https://openalex.org/W2103235956","https://openalex.org/W2176625348","https://openalex.org/W2593116425","https://openalex.org/W2749772809","https://openalex.org/W2759976799","https://openalex.org/W2775794021","https://openalex.org/W2896006068","https://openalex.org/W2907492528","https://openalex.org/W2908510526","https://openalex.org/W2913795158","https://openalex.org/W2921763313","https://openalex.org/W2922137896","https://openalex.org/W2925029759","https://openalex.org/W2950898568","https://openalex.org/W2968661326","https://openalex.org/W2972581694","https://openalex.org/W2972651776","https://openalex.org/W3015420744","https://openalex.org/W3092858428","https://openalex.org/W3094550259","https://openalex.org/W3096787185","https://openalex.org/W3102511045","https://openalex.org/W3164791629","https://openalex.org/W3209974982","https://openalex.org/W4225324023","https://openalex.org/W4285601347","https://openalex.org/W4289286846","https://openalex.org/W4293455017","https://openalex.org/W4295723153","https://openalex.org/W4312445970","https://openalex.org/W4312756816","https://openalex.org/W4313855753","https://openalex.org/W4320919668","https://openalex.org/W4360596622","https://openalex.org/W4362696501","https://openalex.org/W4380995588","https://openalex.org/W4381854917","https://openalex.org/W4385245566","https://openalex.org/W4385823250","https://openalex.org/W4389356607","https://openalex.org/W6690815549","https://openalex.org/W6734260513","https://openalex.org/W6739901393","https://openalex.org/W6751923770","https://openalex.org/W6752516136","https://openalex.org/W6756850094","https://openalex.org/W6758876586","https://openalex.org/W6760395818","https://openalex.org/W6795710243","https://openalex.org/W6803911049","https://openalex.org/W6839843475"],"related_works":["https://openalex.org/W2411659965","https://openalex.org/W2387677326","https://openalex.org/W4200063482","https://openalex.org/W2357575019","https://openalex.org/W2370117122","https://openalex.org/W2360603947","https://openalex.org/W2371528275","https://openalex.org/W2596619385","https://openalex.org/W2945798006","https://openalex.org/W3207420377"],"abstract_inverted_index":{"Most":[0],"deep":[1],"learning-based":[2],"acoustic":[3,12,53,151],"scene":[4],"classification":[5],"(ASC)":[6],"approaches":[7,29],"identify":[8,39],"scenes":[9,54,152],"based":[10,153],"on":[11,47,118,131,154],"features":[13],"converted":[14],"from":[15,58,106],"audio":[16,24,156],"clips":[17],"containing":[18],"mixed":[19],"information":[20],"entangled":[21],"by":[22,113,133,164],"polyphonic":[23],"events":[25],"(AEs).":[26],"However,":[27],"these":[28],"have":[30],"difficulties":[31],"in":[32,88],"explaining":[33],"what":[34],"cues":[35,85,104],"they":[36],"use":[37],"to":[38,75],"scenes.":[40],"This":[41],"paper":[42],"conducts":[43],"the":[44,49,59,91,125,146,155],"first":[45],"study":[46],"disclosing":[48],"relationship":[50,103],"between":[51],"real-life":[52,120],"and":[55,78,82],"semantic":[56],"embeddings":[57,94,135],"most":[60],"relevant":[61],"AEs.":[62,142],"Specifically,":[63],"we":[64],"propose":[65],"an":[66],"event-relational":[67,92,157],"graph":[68,161],"representation":[69],"learning":[70,134],"(ERGL)":[71],"framework":[72],"for":[73],"ASC":[74,121,132],"classify":[76],"scenes,":[77],"simultaneously":[79],"answer":[80],"clearly":[81],"straightly":[83],"which":[84],"are":[86,98,111,166],"used":[87],"classifying.":[89],"In":[90],"graph,":[93],"of":[95,109,136,141,148,160],"each":[96,107],"event":[97],"treated":[99],"as":[100],"nodes,":[101],"while":[102],"derived":[105],"pair":[108],"nodes":[110],"described":[112],"multi-dimensional":[114],"edge":[115],"features.":[116],"Experiments":[117],"a":[119,138],"dataset":[122],"show":[123,145],"that":[124],"proposed":[126],"ERGL":[127,165],"achieves":[128],"competitive":[129],"performance":[130],"only":[137],"limited":[139],"number":[140],"The":[143],"results":[144],"feasibility":[147],"recognizing":[149],"diverse":[150],"graph.":[158],"Visualizations":[159],"representations":[162],"learned":[163],"available":[167],"here":[168],"<uri":[169],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[170],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">(https://github.com/Yuanbo2020/ERGL)</uri>":[171],".":[172]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}