{"id":"https://openalex.org/W2942146535","doi":"https://doi.org/10.21437/interspeech.2019-2169","title":"Towards Joint Sound Scene and Polyphonic Sound Event Recognition","display_name":"Towards Joint Sound Scene and Polyphonic Sound Event Recognition","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2942146535","doi":"https://doi.org/10.21437/interspeech.2019-2169","mag":"2942146535"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-2169","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2169","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","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/1904.10408","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031962033","display_name":"Helen L. Bear","orcid":"https://orcid.org/0000-0002-6051-536X"},"institutions":[{"id":"https://openalex.org/I1118541","display_name":"University of East Anglia","ror":"https://ror.org/026k5mg93","country_code":"GB","type":"education","lineage":["https://openalex.org/I1118541"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Helen L. Bear","raw_affiliation_strings":["University of East Anglia, Norwich, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of East Anglia, Norwich, United Kingdom","institution_ids":["https://openalex.org/I1118541"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008238721","display_name":"In\u00eas Nolasco","orcid":"https://orcid.org/0000-0002-7322-7148"},"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":"In\u00eas Nolasco","raw_affiliation_strings":["Queen Mary University of London, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Queen Mary University of London, London, United Kingdom","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":["Queen Mary University of London, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Queen Mary University of London, London, United Kingdom","institution_ids":["https://openalex.org/I166337079"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5031962033"],"corresponding_institution_ids":["https://openalex.org/I1118541"],"apc_list":null,"apc_paid":null,"fwci":0.3349,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.53614605,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"4594","last_page":"4598"},"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":0.9973999857902527,"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":0.9909999966621399,"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/sound","display_name":"Sound (geography)","score":0.7860945463180542},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.7017725706100464},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6903854608535767},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.5558934211730957},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5342079401016235},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4881196916103363},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4352867603302002},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.28356125950813293},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.062090903520584106}],"concepts":[{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.7860945463180542},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.7017725706100464},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6903854608535767},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.5558934211730957},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5342079401016235},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4881196916103363},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4352867603302002},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.28356125950813293},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.062090903520584106},{"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/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural 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}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.21437/interspeech.2019-2169","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2169","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1904.10408","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.10408","pdf_url":"https://arxiv.org/pdf/1904.10408","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":"","raw_type":"text"},{"id":"mag:2942146535","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1904.10408","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:123456789/58478","is_oa":false,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/58478","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.1904.10408","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1904.10408","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:1904.10408","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.10408","pdf_url":"https://arxiv.org/pdf/1904.10408","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":"","raw_type":"text"},"sustainable_development_goals":[{"score":0.5199999809265137,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"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/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/W2942146535.pdf","grobid_xml":"https://content.openalex.org/works/W2942146535.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W1501987291","https://openalex.org/W2058189943","https://openalex.org/W2086384421","https://openalex.org/W2103235956","https://openalex.org/W2130640900","https://openalex.org/W2133824856","https://openalex.org/W2398243923","https://openalex.org/W2408239454","https://openalex.org/W2557283755","https://openalex.org/W2591013610","https://openalex.org/W2618553051","https://openalex.org/W2619623002","https://openalex.org/W2759976799","https://openalex.org/W2771361008","https://openalex.org/W2775794021","https://openalex.org/W2890685186","https://openalex.org/W2893908923","https://openalex.org/W2900315145","https://openalex.org/W2921763313","https://openalex.org/W2971670255"],"related_works":["https://openalex.org/W3209172644","https://openalex.org/W3015700860","https://openalex.org/W2623700780","https://openalex.org/W2048390151","https://openalex.org/W2020861635","https://openalex.org/W3024440595","https://openalex.org/W3042950341","https://openalex.org/W1493517262","https://openalex.org/W3211325399","https://openalex.org/W3209797185","https://openalex.org/W3210723106","https://openalex.org/W3208958992","https://openalex.org/W3208681643","https://openalex.org/W3208351648","https://openalex.org/W3210197236","https://openalex.org/W3209957988","https://openalex.org/W3209111426","https://openalex.org/W3210572019","https://openalex.org/W3208082774","https://openalex.org/W2341860434"],"abstract_inverted_index":{"Acoustic":[0],"Scene":[1],"Classification":[2],"(ASC)":[3],"and":[4,33,37,50,66],"Sound":[5],"Event":[6],"Detection":[7],"(SED)":[8],"are":[9,69,78],"two":[10],"separate":[11],"tasks":[12],"in":[13,80],"the":[14,84],"field":[15],"of":[16],"computational":[17],"sound":[18,31,34,48,52,73,90],"scene":[19,32],"analysis.":[20],"In":[21],"this":[22,39],"work,":[23],"we":[24],"present":[25],"a":[26,42,59,81],"new":[27],"dataset":[28,82],"with":[29],"both":[30],"event":[35,74],"labels":[36],"use":[38],"to":[40],"demonstrate":[41],"novel":[43],"method":[44],"for":[45,72],"jointly":[46],"classifying":[47],"scenes":[49],"recognizing":[51],"events.":[53],"We":[54],"show":[55],"that":[56],"by":[57],"taking":[58],"joint":[60],"approach,":[61],"learning":[62],"is":[63,87],"more":[64],"efficient":[65],"whilst":[67],"improvements":[68],"still":[70],"needed":[71],"detection,":[75],"SED":[76],"results":[77],"robust":[79],"where":[83],"sample":[85],"distribution":[86],"skewed":[88],"towards":[89],"scenes.":[91]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}