{"id":"https://openalex.org/W4375868875","doi":"https://doi.org/10.1109/icassp49357.2023.10096842","title":"Gct: Gated Contextual Transformer for Sequential Audio Tagging","display_name":"Gct: Gated Contextual Transformer for Sequential Audio Tagging","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375868875","doi":"https://doi.org/10.1109/icassp49357.2023.10096842"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096842","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096842","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://biblio.ugent.be/publication/01HJ3VQADMK9275VW7XRG0Q74E/file/01HJ3VVSPCKTNHA6PWMHHD4BW7.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":false,"raw_author_name":"Yuanbo Hou","raw_affiliation_strings":["WAVES, Ghent University,Belgium","WAVES, Ghent University, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"WAVES, Ghent University,Belgium","institution_ids":["https://openalex.org/I32597200"]},{"raw_affiliation_string":"WAVES, Ghent University, Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100377647","display_name":"Yun Wang","orcid":"https://orcid.org/0000-0002-9732-9245"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yun Wang","raw_affiliation_strings":["Meta AI,USA","Meta AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI,USA","institution_ids":[]},{"raw_affiliation_string":"Meta AI, USA","institution_ids":[]}]},{"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":["CVSSP, University of Surrey,UK","CVSSP, University of Surrey, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CVSSP, University of Surrey,UK","institution_ids":["https://openalex.org/I28290843"]},{"raw_affiliation_string":"CVSSP, University of Surrey, UK","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, Ghent University,Belgium","WAVES, Ghent University, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"WAVES, Ghent University,Belgium","institution_ids":["https://openalex.org/I32597200"]},{"raw_affiliation_string":"WAVES, Ghent University, Belgium","institution_ids":["https://openalex.org/I32597200"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"26","issue":null,"first_page":"1","last_page":"5"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9828000068664551,"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":0.8521990776062012},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6154627799987793},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5543875098228455},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5376296043395996},{"id":"https://openalex.org/keywords/perceptron","display_name":"Perceptron","score":0.5203477740287781},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5181609392166138},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37478601932525635},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3323383331298828},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.27012717723846436}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8521990776062012},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6154627799987793},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5543875098228455},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5376296043395996},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.5203477740287781},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5181609392166138},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37478601932525635},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3323383331298828},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.27012717723846436},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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":2,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096842","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096842","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:archive.ugent.be:01HJ3VQADMK9275VW7XRG0Q74E","is_oa":true,"landing_page_url":"http://hdl.handle.net/1854/LU-01HJ3VQADMK9275VW7XRG0Q74E","pdf_url":"https://biblio.ugent.be/publication/01HJ3VQADMK9275VW7XRG0Q74E/file/01HJ3VVSPCKTNHA6PWMHHD4BW7.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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ISBN: 9781728163277","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:archive.ugent.be:01HJ3VQADMK9275VW7XRG0Q74E","is_oa":true,"landing_page_url":"http://hdl.handle.net/1854/LU-01HJ3VQADMK9275VW7XRG0Q74E","pdf_url":"https://biblio.ugent.be/publication/01HJ3VQADMK9275VW7XRG0Q74E/file/01HJ3VVSPCKTNHA6PWMHHD4BW7.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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ISBN: 9781728163277","raw_type":"info:eu-repo/semantics/conferenceObject"},"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/W4375868875.pdf","grobid_xml":"https://content.openalex.org/works/W4375868875.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W104184427","https://openalex.org/W1535031652","https://openalex.org/W2069143585","https://openalex.org/W2095705004","https://openalex.org/W2096451472","https://openalex.org/W2127141656","https://openalex.org/W2147174722","https://openalex.org/W2408239454","https://openalex.org/W2467206671","https://openalex.org/W2593116425","https://openalex.org/W2618269622","https://openalex.org/W2759976799","https://openalex.org/W2775794021","https://openalex.org/W2899790086","https://openalex.org/W2928717951","https://openalex.org/W2963273475","https://openalex.org/W3023043375","https://openalex.org/W3034772996","https://openalex.org/W3096787185","https://openalex.org/W3097791920","https://openalex.org/W3187295906","https://openalex.org/W3196974791","https://openalex.org/W4289286846","https://openalex.org/W4289329167","https://openalex.org/W4296068423","https://openalex.org/W4385245566","https://openalex.org/W6604254268","https://openalex.org/W6674330103","https://openalex.org/W6674472854","https://openalex.org/W6681474505","https://openalex.org/W6720039734","https://openalex.org/W6739901393","https://openalex.org/W6747106559","https://openalex.org/W6753516609","https://openalex.org/W6756001544","https://openalex.org/W6756850094","https://openalex.org/W6772381481","https://openalex.org/W6777041185","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W2082756648","https://openalex.org/W2055243143","https://openalex.org/W3194278305","https://openalex.org/W2289648981","https://openalex.org/W1565459987","https://openalex.org/W45198419","https://openalex.org/W4206178588","https://openalex.org/W4287635093","https://openalex.org/W3094491777","https://openalex.org/W3214715529"],"abstract_inverted_index":{"Audio":[0],"tagging":[1,20],"aims":[2],"to":[3,7,10,62,127],"assign":[4],"predefined":[5],"tags":[6],"audio":[8,16,19,29,40,139],"clips":[9],"indicate":[11],"the":[12,25,32,39,63,129,136,148,158],"class":[13,26],"information":[14,27,82,93,99],"of":[15,28,131],"events.":[17],"Sequential":[18],"(SAT)":[21],"means":[22],"detecting":[23],"both":[24],"events,":[30],"and":[31,153,161],"order":[33],"in":[34,83,90,100,125],"which":[35],"they":[36],"occur":[37],"within":[38],"clip.":[41],"Most":[42],"existing":[43],"methods":[44,160],"for":[45],"SAT":[46],"are":[47],"based":[48],"on":[49,135],"connectionist":[50],"temporal":[51],"classification":[52],"(CTC).":[53],"However,":[54],"CTC":[55],"cannot":[56],"effectively":[57],"capture":[58],"event":[59],"connections":[60],"due":[61],"conditional":[64],"independence":[65],"assumption":[66],"between":[67],"outputs":[68],"at":[69],"different":[70],"times.":[71],"The":[72],"contextual":[73,81,92,107,118],"Transformer":[74,108],"(cTransformer)":[75],"addresses":[76],"this":[77],"issue":[78],"by":[79],"exploiting":[80,91],"SAT.":[84],"Nevertheless,":[85],"cTransformer":[86,132],"is":[87,123],"also":[88],"limited":[89],"as":[94],"it":[95],"only":[96],"uses":[97],"forward":[98],"inference.":[101],"This":[102],"paper":[103],"proposes":[104],"a":[105,116],"gated":[106,117],"(GCT)":[109],"with":[110,141,151],"forward-backward":[111],"inference":[112],"(FBI).":[113],"In":[114],"addition,":[115],"multi-layer":[119],"perceptron":[120],"(GCMLP)":[121],"block":[122],"proposed":[124,149],"GCT":[126,150],"improve":[128],"performance":[130],"structurally.":[133],"Experiments":[134],"two":[137],"real-life":[138],"datasets":[140],"manually":[142],"annotated":[143],"sequential":[144],"labels":[145],"show":[146],"that":[147],"GCMLP":[152],"FBI":[154],"performs":[155],"better":[156],"than":[157],"CTC-based":[159],"cTransformer.":[162]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}