{"id":"https://openalex.org/W2964947054","doi":"https://doi.org/10.1109/tmm.2019.2933330","title":"Multi-Task Learning for Acoustic Event Detection Using Event and Frame Position Information","display_name":"Multi-Task Learning for Acoustic Event Detection Using Event and Frame Position Information","publication_year":2019,"publication_date":"2019-08-05","ids":{"openalex":"https://openalex.org/W2964947054","doi":"https://doi.org/10.1109/tmm.2019.2933330","mag":"2964947054"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2019.2933330","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2019.2933330","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Transactions on Multimedia","raw_type":"journal-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/A5091584895","display_name":"Xianjun Xia","orcid":"https://orcid.org/0000-0001-5277-6634"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xianjun Xia","raw_affiliation_strings":["The University of Western Australia, Perth, Australia"],"raw_orcid":"https://orcid.org/0000-0001-5277-6634","affiliations":[{"raw_affiliation_string":"The University of Western Australia, Perth, Australia","institution_ids":["https://openalex.org/I177877127"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017213156","display_name":"Roberto Togneri","orcid":"https://orcid.org/0000-0002-3778-4633"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Roberto Togneri","raw_affiliation_strings":["The University of Western Australia, Perth, Australia"],"raw_orcid":"https://orcid.org/0000-0002-3778-4633","affiliations":[{"raw_affiliation_string":"The University of Western Australia, Perth, Australia","institution_ids":["https://openalex.org/I177877127"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002219416","display_name":"Ferdous Sohel","orcid":"https://orcid.org/0000-0003-1557-4907"},"institutions":[{"id":"https://openalex.org/I176790772","display_name":"Murdoch University","ror":"https://ror.org/00r4sry34","country_code":"AU","type":"education","lineage":["https://openalex.org/I176790772"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ferdous Sohel","raw_affiliation_strings":["College of Science, Health Engineering and Education, Murdoch University, Perth, Australia"],"raw_orcid":"https://orcid.org/0000-0003-1557-4907","affiliations":[{"raw_affiliation_string":"College of Science, Health Engineering and Education, Murdoch University, Perth, Australia","institution_ids":["https://openalex.org/I176790772"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101727776","display_name":"Yuanjun Zhao","orcid":"https://orcid.org/0000-0002-6153-3543"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yuanjun Zhao","raw_affiliation_strings":["The University of Western Australia, Perth, Australia"],"raw_orcid":"https://orcid.org/0000-0002-6153-3543","affiliations":[{"raw_affiliation_string":"The University of Western Australia, Perth, Australia","institution_ids":["https://openalex.org/I177877127"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088212422","display_name":"Defeng Huang","orcid":"https://orcid.org/0000-0002-1431-8859"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Defeng Huang","raw_affiliation_strings":["The University of Western Australia, Perth, Australia"],"raw_orcid":"https://orcid.org/0000-0002-1431-8859","affiliations":[{"raw_affiliation_string":"The University of Western Australia, Perth, Australia","institution_ids":["https://openalex.org/I177877127"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.0041,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.92148031,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"22","issue":"3","first_page":"569","last_page":"578"},"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":0.9847999811172485,"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":0.95169997215271,"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":0.8255491852760315},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6248143315315247},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5784146785736084},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5688689351081848},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5272994041442871},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49267059564590454},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.44818827509880066},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.42471209168434143},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38887298107147217}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8255491852760315},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6248143315315247},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5784146785736084},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5688689351081848},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5272994041442871},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49267059564590454},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.44818827509880066},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.42471209168434143},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38887298107147217},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tmm.2019.2933330","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2019.2933330","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Transactions on Multimedia","raw_type":"journal-article"},{"id":"pmh:oai:researchrepository.murdoch.edu.au:55058","is_oa":false,"landing_page_url":"https://researchrepository.murdoch.edu.au/id/eprint/55058/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400274","display_name":"Murdoch Research Repository (Murdoch University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I176790772","host_organization_name":"Murdoch University","host_organization_lineage":["https://openalex.org/I176790772"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"  Xia, X., Togneri, R., Sohel, F. <https://researchrepository.murdoch.edu.au/view/author/Sohel, Ferdous.html>, Zhao, Y. and Huang, D.   (2020)  Multi-Task learning for acoustic event detection using event and frame position information.    IEEE Transactions on Multimedia, 22  (3).   pp. 569-578.  ","raw_type":"Journal Article"},{"id":"pmh:oai:pure.atira.dk:publications/b8ade0e9-17f4-48bb-9f06-1317d21e44af","is_oa":false,"landing_page_url":"http://www.scopus.com/inward/record.url?scp=85080883069&partnerID=8YFLogxK","pdf_url":null,"source":{"id":"https://openalex.org/S4306402492","display_name":"UWA Profiles and Research Repository (UWA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177877127","host_organization_name":"The University of Western Australia","host_organization_lineage":["https://openalex.org/I177877127"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Xia , X , Togneri , R , Sohel , F , Zhao , Y & Huang , D 2020 , ' Multi-Task Learning for Acoustic Event Detection Using Event and Frame Position Information ' , IEEE Transactions on Multimedia , vol. 22 , no. 3 , 8788613 , pp. 569-578 . https://doi.org/10.1109/TMM.2019.2933330","raw_type":"article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320320991","display_name":"University of Western Australia","ror":"https://ror.org/047272k79"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1650531274","https://openalex.org/W1869398109","https://openalex.org/W1900086069","https://openalex.org/W1907729166","https://openalex.org/W2065529590","https://openalex.org/W2083181815","https://openalex.org/W2086384421","https://openalex.org/W2093328288","https://openalex.org/W2105068979","https://openalex.org/W2134426937","https://openalex.org/W2166338096","https://openalex.org/W2341412280","https://openalex.org/W2406600653","https://openalex.org/W2407542046","https://openalex.org/W2515980659","https://openalex.org/W2560096627","https://openalex.org/W2560740363","https://openalex.org/W2566935005","https://openalex.org/W2583115687","https://openalex.org/W2591013610","https://openalex.org/W2622742434","https://openalex.org/W2624871570","https://openalex.org/W2743672024","https://openalex.org/W2745616976","https://openalex.org/W2752592287","https://openalex.org/W2752693731","https://openalex.org/W2763761345","https://openalex.org/W2775505379","https://openalex.org/W2775794021","https://openalex.org/W2794821752","https://openalex.org/W2888678380","https://openalex.org/W2891621134","https://openalex.org/W2900266038","https://openalex.org/W2943940178","https://openalex.org/W2962739470","https://openalex.org/W3103850820","https://openalex.org/W6675872639","https://openalex.org/W6725714497","https://openalex.org/W6739365718","https://openalex.org/W6739564277","https://openalex.org/W6742827142","https://openalex.org/W6744964450","https://openalex.org/W6762573427"],"related_works":["https://openalex.org/W2803309984","https://openalex.org/W2963872552","https://openalex.org/W2237537322","https://openalex.org/W2950678851","https://openalex.org/W2914746235","https://openalex.org/W4301248618","https://openalex.org/W2952195321","https://openalex.org/W2389546251","https://openalex.org/W2043727559","https://openalex.org/W2369556382"],"abstract_inverted_index":{"Acoustic":[0],"event":[1,18,32,55,86],"detection":[2,88],"deals":[3],"with":[4,34,67],"the":[5,10,16,29,41,46,53,58,62,84,90,96,104,110,117,132,136,143,147,161],"acoustic":[6,43,54,85,111],"signals":[7],"to":[8,14,27,39,72,94,113,125,160],"determine":[9,40],"sound":[11],"type":[12,87],"and":[13,89,135,156],"estimate":[15],"audio":[17,63],"boundaries.":[19],"Multi-label":[20],"classification":[21],"based":[22,77],"approaches":[23],"are":[24,49],"commonly":[25],"used":[26],"detect":[28],"frame":[30,59,97],"wise":[31],"types":[33,56],"a":[35,74],"median":[36],"filter":[37],"applied":[38],"happening":[42],"events.":[44,64],"However,":[45],"multi-label":[47],"classifiers":[48],"trained":[50],"only":[51],"on":[52,131],"ignoring":[57],"position":[60,98],"within":[61],"To":[65],"deal":[66],"this,":[68],"this":[69],"paper":[70],"proposes":[71],"construct":[73],"joint":[75,148],"learning":[76,149],"multi-task":[78],"system.":[79,164],"The":[80],"first":[81],"task":[82,92],"performs":[83],"second":[91],"is":[93],"predict":[95],"information.":[99],"By":[100],"sharing":[101],"representations":[102],"between":[103],"two":[105],"tasks,":[106],"we":[107],"can":[108],"enable":[109],"models":[112],"generalize":[114],"better":[115],"than":[116],"original":[118],"classifier":[119],"by":[120,151],"averaging":[121],"respective":[122],"noise":[123],"patterns":[124],"be":[126],"implicitly":[127],"regularized.":[128],"Experimental":[129],"results":[130],"monophonic":[133],"UPC-TALP":[134],"polyphonic":[137],"TUT":[138],"Sound":[139],"Event":[140],"datasets":[141],"demonstrate":[142],"superior":[144],"performance":[145],"of":[146],"method":[150],"achieving":[152],"lower":[153],"error":[154],"rate":[155],"higher":[157],"F-score":[158],"compared":[159],"baseline":[162],"AED":[163]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}