{"id":"https://openalex.org/W4390938782","doi":"https://doi.org/10.1109/lsp.2024.3352514","title":"ATGNN: Audio Tagging Graph Neural Network","display_name":"ATGNN: Audio Tagging Graph Neural Network","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4390938782","doi":"https://doi.org/10.1109/lsp.2024.3352514"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2024.3352514","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2024.3352514","pdf_url":null,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://repository.tilburguniversity.edu/bitstreams/f2d06837-6590-4665-a7ed-5111c29e2629/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060724782","display_name":"Shubhr Singh","orcid":"https://orcid.org/0000-0002-1063-2875"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Shubhr Singh","raw_affiliation_strings":["School of Electronic Engineering and Computer Science, Queen Mary University of London, London, U.K"],"raw_orcid":"https://orcid.org/0000-0002-1063-2875","affiliations":[{"raw_affiliation_string":"School of Electronic Engineering and Computer Science, Queen Mary University of London, London, U.K","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032881514","display_name":"Christian J. Steinmetz","orcid":"https://orcid.org/0000-0002-0971-5729"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Christian J. Steinmetz","raw_affiliation_strings":["School of Electronic Engineering and Computer Science, Queen Mary University of London, London, U.K"],"raw_orcid":"https://orcid.org/0000-0002-0971-5729","affiliations":[{"raw_affiliation_string":"School of Electronic Engineering and Computer Science, Queen Mary University of London, London, U.K","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084672392","display_name":"Emmanouil Benetos","orcid":"https://orcid.org/0000-0002-6820-6764"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Emmanouil Benetos","raw_affiliation_strings":["School of Electronic Engineering and Computer Science, Queen Mary University of London, London, U.K"],"raw_orcid":"https://orcid.org/0000-0002-6820-6764","affiliations":[{"raw_affiliation_string":"School of Electronic Engineering and Computer Science, Queen Mary University of London, London, U.K","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058452657","display_name":"Huy Phan","orcid":"https://orcid.org/0000-0003-4096-785X"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huy Phan","raw_affiliation_strings":["Amazon, Cambridge, MA, USA"],"raw_orcid":"https://orcid.org/0000-0003-4096-785X","affiliations":[{"raw_affiliation_string":"Amazon, Cambridge, MA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005866826","display_name":"Dan Stowell","orcid":"https://orcid.org/0000-0001-8068-3769"},"institutions":[{"id":"https://openalex.org/I193700539","display_name":"Tilburg University","ror":"https://ror.org/04b8v1s79","country_code":"NL","type":"education","lineage":["https://openalex.org/I193700539"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Dan Stowell","raw_affiliation_strings":["Tilburg University, Bijsterveldenlaan, Tilburg, The Netherlands","Tilburg University, Bijsterveldenlaan, Tilburg, AB, Netherlands"],"raw_orcid":"https://orcid.org/0000-0001-8068-3769","affiliations":[{"raw_affiliation_string":"Tilburg University, Bijsterveldenlaan, Tilburg, The Netherlands","institution_ids":["https://openalex.org/I193700539"]},{"raw_affiliation_string":"Tilburg University, Bijsterveldenlaan, Tilburg, AB, Netherlands","institution_ids":["https://openalex.org/I193700539"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.8302,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.95804505,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"31","issue":null,"first_page":"825","last_page":"829"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"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":0.9993000030517578,"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/T10028","display_name":"Topic Modeling","score":0.9944999814033508,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9839000105857849,"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/spectrogram","display_name":"Spectrogram","score":0.8546979427337646},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8007805943489075},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.6072360873222351},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5123942494392395},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4875871539115906},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4760149121284485},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4478415846824646},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4463276267051697},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.37643665075302124},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.17529723048210144}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8546979427337646},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8007805943489075},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.6072360873222351},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5123942494392395},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4875871539115906},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4760149121284485},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4478415846824646},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4463276267051697},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37643665075302124},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.17529723048210144},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/lsp.2024.3352514","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2024.3352514","pdf_url":null,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},{"id":"pmh:oai:tilburguniversity.edu:openaire/60048669-1ea0-4234-8cc1-6841ec8be47e","is_oa":true,"landing_page_url":"https://repository.tilburguniversity.edu/bitstreams/f2d06837-6590-4665-a7ed-5111c29e2629/download","pdf_url":null,"source":{"id":"https://openalex.org/S4406923027","display_name":"Tilburg University Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Singh, S, Steinmetz, C J, Benetos, E, Phan, H & Stowell, D 2024, 'ATGNN : Audio Tagging Graph Neural Network', IEEE Signal Processing Letters, vol. 31, pp. 825-829. https://doi.org/10.1109/LSP.2024.3352514","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:tilburguniversity.edu:openaire_cris_publications/60048669-1ea0-4234-8cc1-6841ec8be47e","is_oa":true,"landing_page_url":"https://research.tilburguniversity.edu/en/publications/60048669-1ea0-4234-8cc1-6841ec8be47e","pdf_url":null,"source":{"id":"https://openalex.org/S4306401490","display_name":"Research portal (Tilburg University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I193700539","host_organization_name":"Tilburg University","host_organization_lineage":["https://openalex.org/I193700539"],"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":"Singh, S, Steinmetz, C J, Benetos, E, Phan, H & Stowell, D 2024, 'ATGNN : Audio Tagging Graph Neural Network', IEEE Signal Processing Letters, vol. 31, pp. 825-829. https://doi.org/10.1109/LSP.2024.3352514","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:tilburguniversity.edu:publications/60048669-1ea0-4234-8cc1-6841ec8be47e","is_oa":true,"landing_page_url":"https://research.tilburguniversity.edu/files/109487772/atgnn.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4406923027","display_name":"Tilburg University Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Singh, S, Steinmetz, C J, Benetos, E, Phan, H & Stowell, D 2024, 'ATGNN : Audio Tagging Graph Neural Network', IEEE Signal Processing Letters, vol. 31, pp. 825-829. https://doi.org/10.1109/LSP.2024.3352514","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:qmro.qmul.ac.uk:123456789/93742","is_oa":false,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/93742","pdf_url":null,"source":{"id":"https://openalex.org/S4306400530","display_name":"Queen Mary Research Online (Queen Mary University of London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I166337079","host_organization_name":"Queen Mary University of London","host_organization_lineage":["https://openalex.org/I166337079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":{"id":"pmh:oai:tilburguniversity.edu:openaire/60048669-1ea0-4234-8cc1-6841ec8be47e","is_oa":true,"landing_page_url":"https://repository.tilburguniversity.edu/bitstreams/f2d06837-6590-4665-a7ed-5111c29e2629/download","pdf_url":null,"source":{"id":"https://openalex.org/S4406923027","display_name":"Tilburg University Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Singh, S, Steinmetz, C J, Benetos, E, Phan, H & Stowell, D 2024, 'ATGNN : Audio Tagging Graph Neural Network', IEEE Signal Processing Letters, vol. 31, pp. 825-829. https://doi.org/10.1109/LSP.2024.3352514","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G161065704","display_name":null,"funder_award_id":"EP/V062107/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G2486651556","display_name":"GraphNEx: Graph Neural Networks for Explainable Artificial Intelligence","funder_award_id":"EP/V062107/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2194775991","https://openalex.org/W2526050071","https://openalex.org/W2593116425","https://openalex.org/W2932399282","https://openalex.org/W2936774411","https://openalex.org/W2990045899","https://openalex.org/W3015867521","https://openalex.org/W3016005489","https://openalex.org/W3016021376","https://openalex.org/W3094550259","https://openalex.org/W3138516171","https://openalex.org/W3158129762","https://openalex.org/W3196974791","https://openalex.org/W3197101920","https://openalex.org/W3204593031","https://openalex.org/W3205475937","https://openalex.org/W3205743929","https://openalex.org/W4205689591","https://openalex.org/W4284898017","https://openalex.org/W4385245566","https://openalex.org/W4386076539","https://openalex.org/W6631190155","https://openalex.org/W6696085341","https://openalex.org/W6745136726","https://openalex.org/W6794463088","https://openalex.org/W6848935878"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2088854863","https://openalex.org/W2011227383","https://openalex.org/W1976719989","https://openalex.org/W2942893872","https://openalex.org/W2065606036","https://openalex.org/W3179495260","https://openalex.org/W2897924318","https://openalex.org/W2138997758"],"abstract_inverted_index":{"Deep":[0],"learning":[1],"models":[2,155],"such":[3],"as":[4,50,80],"CNNs":[5,29,101],"and":[6,83,121,142],"Transformers":[7,33],"have":[8,18],"achieved":[9],"impressive":[10],"performance":[11],"for":[12],"end-to-end":[13],"audio":[14,63,130],"tagging.":[15],"Recent":[16],"works":[17],"shown":[19],"that":[20],"despite":[21],"stacking":[22],"multiple":[23],"layers,":[24],"the":[25,35,48,70,98,103,139,146],"receptive":[26],"field":[27],"of":[28,53,100,108,160],"remains":[30],"severely":[31],"limited.":[32],"on":[34,128,138,145],"other":[36],"hand":[37],"are":[38],"able":[39],"to":[40,60,152],"map":[41],"global":[42,104],"context":[43],"through":[44],"self-attention,":[45],"but":[46,112],"treat":[47,69],"spectrogram":[49,71,123],"a":[51,73,87],"sequence":[52],"patches":[54],"which":[55],"is":[56],"not":[57,95],"flexible":[58,75],"enough":[59],"capture":[61],"irregular":[62],"objects.":[64],"In":[65],"this":[66],"work,":[67],"we":[68],"in":[72],"more":[74],"way":[76],"by":[77],"considering":[78],"it":[79,85,134],"graph":[81,89],"structure":[82],"process":[84],"with":[86,102,156],"novel":[88],"neural":[90],"architecture":[91],"called":[92],"ATGNN.":[93],"ATGNN":[94,127],"only":[96],"combines":[97],"capability":[99],"information":[105],"sharing":[106],"ability":[107],"Graph":[109],"Neural":[110],"Networks,":[111],"also":[113],"maps":[114],"semantic":[115],"relationships":[116],"between":[117],"learnable":[118,161],"class":[119],"embeddings":[120],"corresponding":[122],"regions.":[124],"We":[125],"evaluate":[126],"two":[129],"tagging":[131],"tasks,":[132],"where":[133],"achieves":[135],"0.585":[136],"mAP":[137,144],"FSD50K":[140],"dataset":[141],"0.335":[143],"AudioSet-balanced":[147],"dataset,":[148],"achieving":[149],"comparable":[150],"results":[151],"Transformer":[153],"based":[154],"significantly":[157],"lower":[158],"number":[159],"parameters.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":5}],"updated_date":"2026-07-05T07:55:05.734416","created_date":"2025-10-10T00:00:00"}