{"id":"https://openalex.org/W4296068423","doi":"https://doi.org/10.21437/interspeech.2022-196","title":"CT-SAT: Contextual Transformer for Sequential Audio Tagging","display_name":"CT-SAT: Contextual Transformer for Sequential Audio Tagging","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4296068423","doi":"https://doi.org/10.21437/interspeech.2022-196"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-196","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-196","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://lirias.kuleuven.be/handle/20.500.12942/722645","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/I2801227569","display_name":"Ghent University Hospital","ror":"https://ror.org/00xmkp704","country_code":"BE","type":"healthcare","lineage":["https://openalex.org/I2801227569"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Yuanbo Hou","raw_affiliation_strings":["Ghent University, Belgium","WAVES Research Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ghent University, Belgium","institution_ids":["https://openalex.org/I2801227569"]},{"raw_affiliation_string":"WAVES Research Group","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057325055","display_name":"Zhaoyi Liu","orcid":"https://orcid.org/0000-0003-0697-9080"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Zhaoyi Liu","raw_affiliation_strings":["KU Leuven, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KU Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009435998","display_name":"Bo Soo Kang","orcid":"https://orcid.org/0000-0003-2970-3650"},"institutions":[{"id":"https://openalex.org/I2801227569","display_name":"Ghent University Hospital","ror":"https://ror.org/00xmkp704","country_code":"BE","type":"healthcare","lineage":["https://openalex.org/I2801227569"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Bo Kang","raw_affiliation_strings":["Ghent University, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ghent University, Belgium","institution_ids":["https://openalex.org/I2801227569"]}]},{"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI, USA","institution_ids":[]}]},{"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/I2801227569","display_name":"Ghent University Hospital","ror":"https://ror.org/00xmkp704","country_code":"BE","type":"healthcare","lineage":["https://openalex.org/I2801227569"]}],"countries":["BE"],"is_corresponding":true,"raw_author_name":"Dick Botteldooren","raw_affiliation_strings":["Ghent University, Belgium","WAVES Research Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ghent University, Belgium","institution_ids":["https://openalex.org/I2801227569"]},{"raw_affiliation_string":"WAVES Research Group","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5069519911"],"corresponding_institution_ids":["https://openalex.org/I2801227569"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4147","last_page":"4151"},"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":0.9962999820709229,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9945999979972839,"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/computer-science","display_name":"Computer science","score":0.8373672962188721},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.682939350605011},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5861256718635559},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5447753667831421},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5280588269233704},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5262940526008606},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42846575379371643},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.4181958734989166}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8373672962188721},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.682939350605011},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5861256718635559},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5447753667831421},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5280588269233704},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5262940526008606},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42846575379371643},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.4181958734989166},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","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},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2022-196","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-196","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},{"id":"pmh:oai:lirias2repo.kuleuven.be:20.500.12942/722645","is_oa":true,"landing_page_url":"https://lirias.kuleuven.be/handle/20.500.12942/722645","pdf_url":null,"source":{"id":"https://openalex.org/S7407055369","display_name":"Lirias","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Interspeech Conference, SOUTH KOREA, Incheon, 18-22 September 2022","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:archive.ugent.be:01GMBA3JPV0KX0YXEGDZVFSSMN","is_oa":true,"landing_page_url":"http://hdl.handle.net/1854/LU-01GMBA3JPV0KX0YXEGDZVFSSMN","pdf_url":"https://biblio.ugent.be/publication/01GMBA3JPV0KX0YXEGDZVFSSMN/file/01GMBA8DVTP0GJS01BTKSK8GVC.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":"ISSN: 2308-457X","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:lirias2repo.kuleuven.be:20.500.12942/722645","is_oa":true,"landing_page_url":"https://lirias.kuleuven.be/handle/20.500.12942/722645","pdf_url":null,"source":{"id":"https://openalex.org/S7407055369","display_name":"Lirias","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Interspeech Conference, SOUTH KOREA, Incheon, 18-22 September 2022","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":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W104184427","https://openalex.org/W2095705004","https://openalex.org/W2096451472","https://openalex.org/W2131774270","https://openalex.org/W2147174722","https://openalex.org/W2197404611","https://openalex.org/W2408239454","https://openalex.org/W2467206671","https://openalex.org/W2561826558","https://openalex.org/W2567070169","https://openalex.org/W2591013610","https://openalex.org/W2592944988","https://openalex.org/W2593116425","https://openalex.org/W2618269622","https://openalex.org/W2759976799","https://openalex.org/W2775794021","https://openalex.org/W2886877375","https://openalex.org/W2896457183","https://openalex.org/W2928717951","https://openalex.org/W2954731415","https://openalex.org/W2963273475","https://openalex.org/W2979826702","https://openalex.org/W3023043375","https://openalex.org/W3034772996","https://openalex.org/W3085832277","https://openalex.org/W3160565563","https://openalex.org/W3163035491","https://openalex.org/W3187295906","https://openalex.org/W3196974791","https://openalex.org/W4289286846","https://openalex.org/W4289329167","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2411659965","https://openalex.org/W2387677326","https://openalex.org/W4200063482","https://openalex.org/W17155033","https://openalex.org/W2357575019","https://openalex.org/W2370117122","https://openalex.org/W2360603947","https://openalex.org/W2371528275","https://openalex.org/W2375454309","https://openalex.org/W2374135200"],"abstract_inverted_index":{"Sequential":[0],"audio":[1,12,30,36,59,69,84,123,145,158,163],"event":[2,37,85,116,146,159],"tagging":[3],"can":[4,133],"provide":[5],"not":[6],"only":[7],"the":[8,16,22,65,90,110,120,131,136,141,157],"type":[9],"information":[10,18,82,114,151],"of":[11,24,83,92,115],"events,":[13],"but":[14],"also":[15],"order":[17],"between":[19,57],"events":[20,25],"and":[21,97,112,143,155],"number":[23],"that":[26,107],"occur":[27],"in":[28,75,161],"an":[29],"clip.":[31],"Most":[32],"previous":[33],"works":[34],"on":[35,41,89,119],"sequence":[38,160],"analysis":[39],"rely":[40],"connectionist":[42],"temporal":[43],"classification":[44],"(CTC).":[45],"However,":[46],"CTC's":[47],"conditional":[48],"independence":[49],"assumption":[50],"prevents":[51],"it":[52],"from":[53,140],"effectively":[54,134],"learning":[55],"correlations":[56],"diverse":[58],"events.":[60],"This":[61],"paper":[62],"first":[63],"introduces":[64],"Transformer":[66,101],"into":[67],"sequential":[68],"tagging,":[70],"since":[71],"Transformers":[72],"perform":[73],"well":[74],"sequence-related":[76],"tasks.":[77],"To":[78],"better":[79],"utilize":[80],"contextual":[81,100,150],"sequences,":[86],"we":[87],"draw":[88],"idea":[91],"bidirectional":[93,105],"recurrent":[94],"neural":[95],"networks,":[96],"propose":[98],"a":[99,104],"(cTransformer)":[102],"with":[103],"decoder":[106],"could":[108],"exploit":[109,149],"forward":[111],"backward":[113],"sequences.":[117],"Experiments":[118],"real-life":[121],"polyphonic":[122,162],"dataset":[124],"show":[125],"that,":[126],"compared":[127],"to":[128,148,152],"CTC-based":[129],"methods,":[130],"cTransformer":[132],"combine":[135],"fine-grained":[137],"acoustic":[138],"representations":[139],"encoder":[142],"coarse-grained":[144],"cues":[147],"successfully":[153],"recognize":[154],"predict":[156],"clips.":[164]},"counts_by_year":[{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
