{"id":"https://openalex.org/W2898875611","doi":"https://doi.org/10.1109/icassp.2019.8683064","title":"Unifying Isolated and Overlapping Audio Event Detection with Multi-label Multi-task Convolutional Recurrent Neural Networks","display_name":"Unifying Isolated and Overlapping Audio Event Detection with Multi-label Multi-task Convolutional Recurrent Neural Networks","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2898875611","doi":"https://doi.org/10.1109/icassp.2019.8683064","mag":"2898875611"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683064","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683064","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1811.01092","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058452657","display_name":"Huy Phan","orcid":"https://orcid.org/0000-0003-4096-785X"},"institutions":[{"id":"https://openalex.org/I20581793","display_name":"University of Kent","ror":"https://ror.org/00xkeyj56","country_code":"GB","type":"education","lineage":["https://openalex.org/I20581793"]},{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Huy Phan","raw_affiliation_strings":["School of Computing, University of Kent, UK","Department of Engineering Science, University of Oxford,#N#UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, University of Kent, UK","institution_ids":["https://openalex.org/I20581793"]},{"raw_affiliation_string":"Department of Engineering Science, University of Oxford,#N#UK","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074236126","display_name":"Oliver Y. Ch\u00e9n","orcid":"https://orcid.org/0000-0002-5696-3127"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Oliver Y. Chen","raw_affiliation_strings":["Department of Engineering Science, University of Oxford, UK","Department of Engineering Science, University of Oxford,#N#UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Engineering Science, University of Oxford, UK","institution_ids":["https://openalex.org/I40120149"]},{"raw_affiliation_string":"Department of Engineering Science, University of Oxford,#N#UK","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044840858","display_name":"Philipp Koch","orcid":"https://orcid.org/0000-0002-8795-758X"},"institutions":[{"id":"https://openalex.org/I9341345","display_name":"University of L\u00fcbeck","ror":"https://ror.org/00t3r8h32","country_code":"DE","type":"education","lineage":["https://openalex.org/I9341345"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Philipp Koch","raw_affiliation_strings":["Institute for Signal Processing, University of L\u00fcbeck, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Signal Processing, University of L\u00fcbeck, Germany","institution_ids":["https://openalex.org/I9341345"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075250567","display_name":"Lam Pham","orcid":"https://orcid.org/0000-0001-8155-7553"},"institutions":[{"id":"https://openalex.org/I20581793","display_name":"University of Kent","ror":"https://ror.org/00xkeyj56","country_code":"GB","type":"education","lineage":["https://openalex.org/I20581793"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Lam Pham","raw_affiliation_strings":["School of Computing, University of Kent, UK","School of Computing, University of Kent (UK)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, University of Kent, UK","institution_ids":["https://openalex.org/I20581793"]},{"raw_affiliation_string":"School of Computing, University of Kent (UK)","institution_ids":["https://openalex.org/I20581793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000620878","display_name":"Ian McLoughlin","orcid":"https://orcid.org/0000-0001-7111-2008"},"institutions":[{"id":"https://openalex.org/I20581793","display_name":"University of Kent","ror":"https://ror.org/00xkeyj56","country_code":"GB","type":"education","lineage":["https://openalex.org/I20581793"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ian McLoughlin","raw_affiliation_strings":["School of Computing, University of Kent, UK","School of Computing, University of Kent (UK)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, University of Kent, UK","institution_ids":["https://openalex.org/I20581793"]},{"raw_affiliation_string":"School of Computing, University of Kent (UK)","institution_ids":["https://openalex.org/I20581793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063948113","display_name":"Alfred Mertins","orcid":"https://orcid.org/0000-0001-5718-577X"},"institutions":[{"id":"https://openalex.org/I9341345","display_name":"University of L\u00fcbeck","ror":"https://ror.org/00t3r8h32","country_code":"DE","type":"education","lineage":["https://openalex.org/I9341345"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alfred Mertins","raw_affiliation_strings":["Institute for Signal Processing, University of L\u00fcbeck, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Signal Processing, University of L\u00fcbeck, Germany","institution_ids":["https://openalex.org/I9341345"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064593698","display_name":"Maarten De Vos","orcid":"https://orcid.org/0000-0002-3482-5145"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Maarten De Vos","raw_affiliation_strings":["Department of Engineering Science, University of Oxford, UK","Department of Engineering Science, University of Oxford,#N#UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Engineering Science, University of Oxford, UK","institution_ids":["https://openalex.org/I40120149"]},{"raw_affiliation_string":"Department of Engineering Science, University of Oxford,#N#UK","institution_ids":["https://openalex.org/I40120149"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3824,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.46388075,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"51","last_page":"55"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9902999997138977,"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":0.9800000190734863,"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":0.8103654980659485},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.7300052046775818},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.632994532585144},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6247425675392151},{"id":"https://openalex.org/keywords/offset","display_name":"Offset (computer science)","score":0.5942327976226807},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5333499908447266},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5196679830551147},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4523202180862427},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.43515291810035706},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41877281665802},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4179798364639282},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3923989236354828},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3386719822883606},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07286366820335388}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8103654980659485},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.7300052046775818},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.632994532585144},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6247425675392151},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.5942327976226807},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5333499908447266},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5196679830551147},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4523202180862427},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.43515291810035706},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41877281665802},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4179798364639282},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3923989236354828},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3386719822883606},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07286366820335388},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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":6,"locations":[{"id":"doi:10.1109/icassp.2019.8683064","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683064","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:kar.kent.ac.uk:72657","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ICASSP.2019.8683064>)","pdf_url":null,"source":{"id":"https://openalex.org/S4377196264","display_name":"Kent Academic Repository (University of Kent)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I20581793","host_organization_name":"University of Kent","host_organization_lineage":["https://openalex.org/I20581793"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Conference proceeding"},{"id":"pmh:oai:arXiv.org:1811.01092","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1811.01092","pdf_url":"https://arxiv.org/pdf/1811.01092","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2898875611","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1811.01092","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:serval.unil.ch:BIB_F143DE7963CD","is_oa":false,"landing_page_url":"https://serval.unil.ch/notice/serval:BIB_F143DE7963CD","pdf_url":null,"source":{"id":"https://openalex.org/S4306401797","display_name":"SERVAL (Universit\u00e9 de Lausanne)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210093590","host_organization_name":"Swiss School of Archaeology in Greece","host_organization_lineage":["https://openalex.org/I4210093590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 51-55","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"doi:10.48550/arxiv.1811.01092","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1811.01092","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1811.01092","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1811.01092","pdf_url":"https://arxiv.org/pdf/1811.01092","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1484767381","https://openalex.org/W1511170870","https://openalex.org/W1650531274","https://openalex.org/W1970578576","https://openalex.org/W1987011838","https://openalex.org/W2034215399","https://openalex.org/W2046972719","https://openalex.org/W2065529590","https://openalex.org/W2086384421","https://openalex.org/W2105068979","https://openalex.org/W2157331557","https://openalex.org/W2172073751","https://openalex.org/W2180653312","https://openalex.org/W2341412280","https://openalex.org/W2562770010","https://openalex.org/W2591013610","https://openalex.org/W2618657287","https://openalex.org/W2754744771","https://openalex.org/W2775482966","https://openalex.org/W2775794021","https://openalex.org/W2794821752","https://openalex.org/W2804233018","https://openalex.org/W2889262746","https://openalex.org/W2964066126","https://openalex.org/W6631190155","https://openalex.org/W6637242042","https://openalex.org/W6638667902","https://openalex.org/W6725714497","https://openalex.org/W6741024066","https://openalex.org/W6742827142","https://openalex.org/W6788837655"],"related_works":["https://openalex.org/W2963794569","https://openalex.org/W3195550707","https://openalex.org/W2995135322","https://openalex.org/W3167679522","https://openalex.org/W3040056597","https://openalex.org/W2964066126","https://openalex.org/W3041391240","https://openalex.org/W2952133361","https://openalex.org/W3133991944","https://openalex.org/W2804233018","https://openalex.org/W2963128891","https://openalex.org/W2799768828","https://openalex.org/W2186025005","https://openalex.org/W3096841046","https://openalex.org/W2913189099","https://openalex.org/W2948510438","https://openalex.org/W2407005679","https://openalex.org/W2592944988","https://openalex.org/W2929703785","https://openalex.org/W2777468850"],"abstract_inverted_index":{"We":[0,115,133],"propose":[1],"a":[2,8],"multi-label":[3,124],"multi-task":[4],"framework":[5,23],"based":[6],"on":[7,137],"convolutional":[9,28,33],"recurrent":[10,29,41,65,112],"neural":[11,30],"network":[12,31,90,122],"to":[13,52,73,79],"unify":[14],"detection":[15],"of":[16,27,56,77,96],"isolated":[17,142],"and":[18,84,100,107,130,146],"overlapping":[19,149],"audio":[20,143,150],"events.":[21],"The":[22],"leverages":[24],"the":[25,47,64,89],"power":[26],"architectures;":[32],"layers":[34,42],"learn":[35],"effective":[36],"features":[37],"over":[38],"which":[39],"higher":[40],"perform":[43],"sequential":[44,119],"modelling.":[45],"Furthermore,":[46],"output":[48,66,69],"layer":[49],"is":[50,71],"designed":[51],"handle":[53],"arbitrary":[54],"degrees":[55],"event":[57,75,82,95,144,151],"overlap.":[58],"At":[59],"each":[60,74,111],"time":[61,113],"step":[62],"in":[63],"sequence,":[67],"an":[68,94],"triple":[70],"dedicated":[72],"category":[76,98],"interest":[78],"jointly":[80,91],"model":[81],"occurrence":[83],"temporal":[85],"boundaries.":[86],"That":[87],"is,":[88],"determines":[92],"whether":[93],"this":[97],"occurs,":[99,103],"when":[101],"it":[102],"by":[104],"estimating":[105],"onset":[106],"offset":[108],"positions":[109],"at":[110],"step.":[114],"then":[116],"introduce":[117],"three":[118],"losses":[120],"for":[121,141,148],"training:":[123],"classification":[125],"loss,":[126,129],"distance":[127],"estimation":[128],"confidence":[131],"loss.":[132],"demonstrate":[134],"good":[135],"generalization":[136],"two":[138],"datasets:":[139],"ITC-Irst":[140],"detection,":[145],"TUT-SED-Synthetic-2016":[147],"detection.":[152]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}