{"id":"https://openalex.org/W2529483679","doi":"https://doi.org/10.1109/icassp.2017.7952234","title":"A joint detection-classification model for audio tagging of weakly labelled data","display_name":"A joint detection-classification model for audio tagging of weakly labelled data","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2529483679","doi":"https://doi.org/10.1109/icassp.2017.7952234","mag":"2529483679"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7952234","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7952234","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5072482416","display_name":"Qiuqiang Kong","orcid":"https://orcid.org/0000-0003-2864-0475"},"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"]},{"id":"https://openalex.org/I4210121626","display_name":"Signal Processing (United States)","ror":"https://ror.org/021gzyw51","country_code":"US","type":"company","lineage":["https://openalex.org/I4210121626"]}],"countries":["GB","US"],"is_corresponding":true,"raw_author_name":"Qiuqiang Kong","raw_affiliation_strings":["Center for Vision, Speech and Signal Processing (CVSSP), University of Surrey"],"affiliations":[{"raw_affiliation_string":"Center for Vision, Speech and Signal Processing (CVSSP), University of Surrey","institution_ids":["https://openalex.org/I28290843","https://openalex.org/I4210121626"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101467338","display_name":"Yong Xu","orcid":"https://orcid.org/0000-0003-4944-6890"},"institutions":[{"id":"https://openalex.org/I4210121626","display_name":"Signal Processing (United States)","ror":"https://ror.org/021gzyw51","country_code":"US","type":"company","lineage":["https://openalex.org/I4210121626"]},{"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","US"],"is_corresponding":false,"raw_author_name":"Yong Xu","raw_affiliation_strings":["Center for Vision, Speech and Signal Processing (CVSSP), University of Surrey"],"affiliations":[{"raw_affiliation_string":"Center for Vision, Speech and Signal Processing (CVSSP), University of Surrey","institution_ids":["https://openalex.org/I28290843","https://openalex.org/I4210121626"]}]},{"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/I4210121626","display_name":"Signal Processing (United States)","ror":"https://ror.org/021gzyw51","country_code":"US","type":"company","lineage":["https://openalex.org/I4210121626"]},{"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","US"],"is_corresponding":false,"raw_author_name":"Wenwu Wang","raw_affiliation_strings":["Center for Vision, Speech and Signal Processing (CVSSP), University of Surrey"],"affiliations":[{"raw_affiliation_string":"Center for Vision, Speech and Signal Processing (CVSSP), University of Surrey","institution_ids":["https://openalex.org/I28290843","https://openalex.org/I4210121626"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066967599","display_name":"Mark D. Plumbley","orcid":"https://orcid.org/0000-0002-9708-1075"},"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"]},{"id":"https://openalex.org/I4210121626","display_name":"Signal Processing (United States)","ror":"https://ror.org/021gzyw51","country_code":"US","type":"company","lineage":["https://openalex.org/I4210121626"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Mark D. Plumbley","raw_affiliation_strings":["Center for Vision, Speech and Signal Processing (CVSSP), University of Surrey"],"affiliations":[{"raw_affiliation_string":"Center for Vision, Speech and Signal Processing (CVSSP), University of Surrey","institution_ids":["https://openalex.org/I28290843","https://openalex.org/I4210121626"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5072482416"],"corresponding_institution_ids":["https://openalex.org/I28290843","https://openalex.org/I4210121626"],"apc_list":null,"apc_paid":null,"fwci":4.8503,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.96043043,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"641","last_page":"645"},"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":0.9983999729156494,"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":0.9897000193595886,"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/joint","display_name":"Joint (building)","score":0.73847496509552},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7314463257789612},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5222581028938293},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4505593478679657},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42211493849754333},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.40487390756607056},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.11601564288139343},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08558076620101929}],"concepts":[{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.73847496509552},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7314463257789612},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5222581028938293},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4505593478679657},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42211493849754333},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40487390756607056},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.11601564288139343},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08558076620101929},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2017.7952234","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7952234","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:alma.44SUR_INST:11139450440002346","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4210197018","display_name":"View","issn_l":"2688-268X","issn":["2688-268X","2688-3988"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:epubs.surrey.ac.uk:813128","is_oa":false,"landing_page_url":"http://epubs.surrey.ac.uk/813128/1/A%20joint%20detection-classification%20model%20for%20audio%20tagging%20of%20weakly%20labelled%20data%20v0.6.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400680","display_name":"Surrey Research Insight Open Access (The University of Surrey)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28290843","host_organization_name":"University of Surrey","host_organization_lineage":["https://openalex.org/I28290843"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8995825145","display_name":null,"funder_award_id":"EP/N014111/1","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":21,"referenced_works":["https://openalex.org/W80364729","https://openalex.org/W1583001605","https://openalex.org/W1974836130","https://openalex.org/W2086384421","https://openalex.org/W2122052811","https://openalex.org/W2123843894","https://openalex.org/W2163605009","https://openalex.org/W2168441989","https://openalex.org/W2176625348","https://openalex.org/W2232894815","https://openalex.org/W2341412280","https://openalex.org/W2354870669","https://openalex.org/W2403172465","https://openalex.org/W2414894569","https://openalex.org/W2470628481","https://openalex.org/W2566935005","https://openalex.org/W2618602706","https://openalex.org/W3103314642","https://openalex.org/W6677993624","https://openalex.org/W6684191040","https://openalex.org/W6980901144"],"related_works":["https://openalex.org/W1996130883","https://openalex.org/W2748574964","https://openalex.org/W2888483922","https://openalex.org/W2367747139","https://openalex.org/W4391102217","https://openalex.org/W2566187525","https://openalex.org/W2367150592","https://openalex.org/W2378889330","https://openalex.org/W2033914206","https://openalex.org/W2042327336"],"abstract_inverted_index":{"Audio":[0],"tagging":[1],"aims":[2],"to":[3,9,61,94,108,110,144],"assign":[4],"one":[5],"or":[6],"several":[7],"tags":[8,24,75],"an":[10,41],"audio":[11,42,49,99,149],"clip.":[12],"Most":[13],"of":[14,25,35,40,70],"the":[15,23,26,32,36,48,52,62,68,74,78,83,98,106,127,133,137,148,157],"datasets":[16],"are":[17,28,120],"weakly":[18],"labelled,":[19],"which":[20,80],"means":[21],"only":[22,117],"clip":[27,43,53,100],"known,":[29],"without":[30,155],"knowing":[31],"occurrence":[33],"time":[34],"tags.":[37],"The":[38,102],"labeling":[39],"is":[44,59,81,152],"often":[45],"based":[46],"on":[47,126],"events":[50],"in":[51,85],"and":[54,96,112],"no":[55],"event":[56,150,158],"level":[57,159],"label":[58],"provided":[60],"user.":[63],"Previous":[64],"works":[65],"have":[66],"used":[67,121],"bag":[69],"frames":[71],"model":[72,93,104,135],"assume":[73],"occur":[76],"all":[77],"time,":[79],"not":[82],"case":[84],"practice.":[86],"We":[87],"propose":[88],"a":[89],"joint":[90],"detection-classification":[91],"(JDC)":[92],"detect":[95],"classify":[97],"simultaneously.":[101],"JDC":[103,134],"has":[105],"ability":[107],"attend":[109],"informative":[111,118],"ignore":[113],"uninformative":[114],"sounds.":[115],"Then":[116],"regions":[119],"for":[122],"classification.":[123],"Experimental":[124],"results":[125],"\u201cCHiME":[128],"Home\u201d":[129],"dataset":[130],"show":[131],"that":[132],"reduces":[136],"equal":[138],"error":[139],"rate":[140],"(EER)":[141],"from":[142],"19.0%":[143],"16.9%.":[145],"More":[146],"interestingly,":[147],"detector":[151],"trained":[153],"successfully":[154],"needing":[156],"label.":[160]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":5}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
