{"id":"https://openalex.org/W2959730436","doi":"https://doi.org/10.1109/waspaa.2019.8937193","title":"Polyphonic Sound Event and Sound Activity Detection: A Multi-Task Approach","display_name":"Polyphonic Sound Event and Sound Activity Detection: A Multi-Task Approach","publication_year":2019,"publication_date":"2019-10-01","ids":{"openalex":"https://openalex.org/W2959730436","doi":"https://doi.org/10.1109/waspaa.2019.8937193","mag":"2959730436"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa.2019.8937193","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa.2019.8937193","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1907.05122","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091748859","display_name":"Arjun Pankajakshan","orcid":null},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Arjun Pankajakshan","raw_affiliation_strings":["School of EECS, Queen Mary University of London, UK","Queen Mary University of London,School of EECS,UK"],"affiliations":[{"raw_affiliation_string":"School of EECS, Queen Mary University of London, UK","institution_ids":["https://openalex.org/I166337079"]},{"raw_affiliation_string":"Queen Mary University of London,School of EECS,UK","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031962033","display_name":"Helen L. Bear","orcid":"https://orcid.org/0000-0002-6051-536X"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Helen L. Bear","raw_affiliation_strings":["School of EECS, Queen Mary University of London, UK","Queen Mary University of London,School of EECS,UK"],"affiliations":[{"raw_affiliation_string":"School of EECS, Queen Mary University of London, UK","institution_ids":["https://openalex.org/I166337079"]},{"raw_affiliation_string":"Queen Mary University of London,School of EECS,UK","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084672392","display_name":"Emmanouil Benetos","orcid":null},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Emmanouil Benetos","raw_affiliation_strings":["School of EECS, Queen Mary University of London, UK","Queen Mary University of London,School of EECS,UK"],"affiliations":[{"raw_affiliation_string":"School of EECS, Queen Mary University of London, UK","institution_ids":["https://openalex.org/I166337079"]},{"raw_affiliation_string":"Queen Mary University of London,School of EECS,UK","institution_ids":["https://openalex.org/I166337079"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5091748859"],"corresponding_institution_ids":["https://openalex.org/I166337079"],"apc_list":null,"apc_paid":null,"fwci":0.3351,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.54796192,"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":"323","last_page":"327"},"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":0.9980999827384949,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.994700014591217,"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":0.7562041282653809},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.7074921131134033},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.7044762969017029},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6587849855422974},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6079800724983215},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5640989542007446},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5364528298377991},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.4942012131214142},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37801122665405273},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.18031755089759827},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08052271604537964},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0788455605506897}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7562041282653809},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.7074921131134033},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.7044762969017029},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6587849855422974},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6079800724983215},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5640989542007446},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5364528298377991},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.4942012131214142},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37801122665405273},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.18031755089759827},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08052271604537964},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0788455605506897},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/waspaa.2019.8937193","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa.2019.8937193","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1907.05122","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1907.05122","pdf_url":"https://arxiv.org/pdf/1907.05122","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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:2959730436","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1907.05122","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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:qmro.qmul.ac.uk:123456789/59068","is_oa":false,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/59068","pdf_url":null,"source":{"id":"https://openalex.org/S4306400530","display_name":"Queen Mary Research Online (Queen Mary University of London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I166337079","host_organization_name":"Queen Mary University of London","host_organization_lineage":["https://openalex.org/I166337079"],"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 Proceeding"},{"id":"doi:10.48550/arxiv.1907.05122","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1907.05122","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1907.05122","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1907.05122","pdf_url":"https://arxiv.org/pdf/1907.05122","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":[{"id":"https://metadata.un.org/sdg/11","score":0.7900000214576721,"display_name":"Sustainable cities and communities"}],"awards":[{"id":"https://openalex.org/G1944538486","display_name":null,"funder_award_id":"EP/R01891X/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2959730436.pdf","grobid_xml":"https://content.openalex.org/works/W2959730436.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W821549425","https://openalex.org/W1522301498","https://openalex.org/W1568645074","https://openalex.org/W2095705004","https://openalex.org/W2106241685","https://openalex.org/W2147917435","https://openalex.org/W2191779130","https://openalex.org/W2196961052","https://openalex.org/W2402144811","https://openalex.org/W2408239454","https://openalex.org/W2565911560","https://openalex.org/W2591013610","https://openalex.org/W2604465723","https://openalex.org/W2758870122","https://openalex.org/W2759976799","https://openalex.org/W2763971240","https://openalex.org/W2767754137","https://openalex.org/W2771361008","https://openalex.org/W2799768828","https://openalex.org/W2888678380","https://openalex.org/W2949117887","https://openalex.org/W2963022469","https://openalex.org/W2963517948","https://openalex.org/W2963551352","https://openalex.org/W2963723765","https://openalex.org/W6631190155","https://openalex.org/W6638667902","https://openalex.org/W6674330103","https://openalex.org/W6713134421","https://openalex.org/W6745117180","https://openalex.org/W6745851314"],"related_works":["https://openalex.org/W2997892289","https://openalex.org/W3091667472","https://openalex.org/W3037561038","https://openalex.org/W2123843894","https://openalex.org/W3095436956","https://openalex.org/W2942551338","https://openalex.org/W3162176995","https://openalex.org/W2408239454","https://openalex.org/W3005741390","https://openalex.org/W2937959246","https://openalex.org/W2622742434","https://openalex.org/W3020280941","https://openalex.org/W2512383693","https://openalex.org/W3160950290","https://openalex.org/W2962999716","https://openalex.org/W3098319575","https://openalex.org/W2754744771","https://openalex.org/W3092858428","https://openalex.org/W3033731578","https://openalex.org/W2745616976"],"abstract_inverted_index":{"Polyphonic":[0],"Sound":[1],"Event":[2,106],"Detection":[3,107,132],"(SED)":[4,108],"in":[5],"real-world":[6],"recordings":[7],"is":[8,58,119],"a":[9,71,84,116,145],"challenging":[10],"task":[11,90,113,155],"because":[12],"of":[13,21,34,80,148],"the":[14,31,54,62,77,111,137,160,165,182,185],"dynamic":[15],"polyphony":[16],"level,":[17],"intensity,":[18],"and":[19,38,174,179,184],"duration":[20],"sound":[22,35,45,81,93,117],"events.":[23],"Current":[24],"polyphonic":[25],"SED":[26],"systems":[27],"fail":[28],"to":[29,41,75],"model":[30,73,140,168],"temporal":[32,78],"structure":[33],"events":[36,46,82,94],"explicitly":[37],"instead":[39],"attempt":[40],"look":[42],"at":[43,49,97,123],"which":[44,92],"are":[47,95],"present":[48,96,120],"each":[50,98,124],"audio":[51],"frame.":[52],"Consequently,":[53],"event-wise":[55,186],"detection":[56,64],"performance":[57],"much":[59],"lower":[60],"than":[61],"segment-wise":[63,183],"performance.":[65],"In":[66],"this":[67,103,128],"work,":[68],"we":[69,101,126],"propose":[70],"joint":[72,139,167],"approach":[74],"improve":[76,180],"localization":[79],"using":[83],"multi-task":[85],"learning":[86],"setup.":[87],"The":[88],"first":[89],"predicts":[91,114],"time":[99],"frame;":[100,125],"call":[102,127],"branch":[104,129],"`Sound":[105,130],"model',":[109],"while":[110],"second":[112],"if":[115],"event":[118],"or":[121],"not":[122],"Activity":[131],"(SAD)":[133],"model'.":[134],"We":[135],"verify":[136],"proposed":[138,166],"by":[141],"comparing":[142],"it":[143],"with":[144],"separate":[146],"implementation":[147],"both":[149,181],"tasks":[150],"aggregated":[151],"together":[152],"from":[153],"individual":[154],"predictions.":[156],"Our":[157],"experiments":[158],"on":[159],"URBAN-SED":[161],"dataset":[162],"show":[163],"that":[164],"can":[169],"alleviate":[170],"False":[171,175],"Positive":[172],"(FP)":[173],"Negative":[176],"(FN)":[177],"errors":[178],"metrics.":[187]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
