{"id":"https://openalex.org/W3015419319","doi":"https://doi.org/10.1109/icassp40776.2020.9053972","title":"Multi-Label Sound Event Retrieval Using A Deep Learning-Based Siamese Structure With A Pairwise Presence Matrix","display_name":"Multi-Label Sound Event Retrieval Using A Deep Learning-Based Siamese Structure With A Pairwise Presence Matrix","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015419319","doi":"https://doi.org/10.1109/icassp40776.2020.9053972","mag":"3015419319"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053972","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053972","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5033210778","display_name":"Jianyu Fan","orcid":null},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Jianyu Fan","raw_affiliation_strings":["Simon Fraser University, Surrey, BC, Canada"],"affiliations":[{"raw_affiliation_string":"Simon Fraser University, Surrey, BC, Canada","institution_ids":["https://openalex.org/I18014758"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056903330","display_name":"Eric Nichols","orcid":"https://orcid.org/0000-0003-0734-6621"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric Nichols","raw_affiliation_strings":["Dynamics 365 AI Research, Microsoft, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Dynamics 365 AI Research, Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051930827","display_name":"Daniel Tompkins","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Tompkins","raw_affiliation_strings":["Dynamics 365 AI Research, Microsoft, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Dynamics 365 AI Research, Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040801874","display_name":"Ana Elisa M\u00e9ndez M\u00e9ndez","orcid":"https://orcid.org/0000-0002-4861-5616"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ana Elisa Mendez Mendez","raw_affiliation_strings":["Dynamics 365 AI Research, Microsoft, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Dynamics 365 AI Research, Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073250019","display_name":"Benjamin Elizalde","orcid":"https://orcid.org/0000-0001-6461-5790"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Benjamin Elizalde","raw_affiliation_strings":["Dynamics 365 AI Research, Microsoft, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Dynamics 365 AI Research, Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022966906","display_name":"Philippe Pasquier","orcid":"https://orcid.org/0000-0001-8675-3561"},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Philippe Pasquier","raw_affiliation_strings":["Simon Fraser University, Surrey, BC, Canada"],"affiliations":[{"raw_affiliation_string":"Simon Fraser University, Surrey, BC, Canada","institution_ids":["https://openalex.org/I18014758"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5033210778"],"corresponding_institution_ids":["https://openalex.org/I18014758"],"apc_list":null,"apc_paid":null,"fwci":0.3031,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.51468071,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.9907000064849854,"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":0.9904999732971191,"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/pairwise-comparison","display_name":"Pairwise comparison","score":0.7250550985336304},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7023600339889526},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6158466339111328},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.601061999797821},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.4677294194698334},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4511881172657013},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.4500853419303894},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37605148553848267},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.06975871324539185}],"concepts":[{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.7250550985336304},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7023600339889526},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6158466339111328},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.601061999797821},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.4677294194698334},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4511881172657013},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4500853419303894},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37605148553848267},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.06975871324539185},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","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/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"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":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053972","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053972","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2047411082","https://openalex.org/W2047484428","https://openalex.org/W2074188409","https://openalex.org/W2103861099","https://openalex.org/W2153894711","https://openalex.org/W2157364932","https://openalex.org/W2401100696","https://openalex.org/W2510940142","https://openalex.org/W2526050071","https://openalex.org/W2563373261","https://openalex.org/W2767252287","https://openalex.org/W2791956393","https://openalex.org/W2887057599","https://openalex.org/W2891575704","https://openalex.org/W2912056372","https://openalex.org/W2940092410","https://openalex.org/W2945263634","https://openalex.org/W2963022469","https://openalex.org/W2964287480","https://openalex.org/W3123940584","https://openalex.org/W4285719527","https://openalex.org/W6712990459","https://openalex.org/W6731112138","https://openalex.org/W6745181628","https://openalex.org/W6749158954","https://openalex.org/W6788837655"],"related_works":["https://openalex.org/W2487162673","https://openalex.org/W2942366970","https://openalex.org/W2793211469","https://openalex.org/W2949152769","https://openalex.org/W4372354731","https://openalex.org/W2562400057","https://openalex.org/W1692008701","https://openalex.org/W2597588799","https://openalex.org/W4360593462","https://openalex.org/W2194570607"],"abstract_inverted_index":{"Realistic":[0],"recordings":[1,69],"of":[2,24,45,120],"soundscapes":[3],"often":[4],"have":[5,52],"multiple":[6,71],"sound":[7,48,61,72],"events":[8,73],"co-occurring,":[9],"such":[10],"as":[11],"car":[12],"horns,":[13],"engine":[14],"and":[15,92,101,110],"human":[16],"voices.":[17],"Sound":[18],"event":[19,49,62],"retrieval":[20,50],"is":[21],"a":[22,90,93],"type":[23],"contentbased":[25],"search":[26],"aiming":[27],"at":[28],"finding":[29],"audio":[30,35,56,68],"samples,":[31],"similar":[32],"to":[33],"an":[34],"query":[36],"based":[37],"on":[38,54,66],"their":[39],"acoustic":[40],"or":[41],"semantic":[42],"content.":[43],"State":[44],"the":[46,104,118],"art":[47],"models":[51],"focused":[53],"single-label":[55],"recordings,":[57],"with":[58,89],"only":[59],"one":[60,76],"occurring,":[63],"rather":[64],"than":[65],"multi-label":[67,111],"(i.e.,":[70],"occur":[74],"in":[75],"recording).":[77],"To":[78],"address":[79],"this":[80],"latter":[81],"problem,":[82],"we":[83],"propose":[84],"different":[85],"Deep":[86],"Learning":[87],"architectures":[88],"Siamesestructure":[91],"Pairwise":[94],"Presence":[95],"Matrix.":[96],"The":[97,114],"networks":[98],"are":[99],"trained":[100],"evaluated":[102],"using":[103],"SONYC-UST":[105],"dataset":[106],"containing":[107],"both":[108],"single-":[109],"soundscape":[112],"recordings.":[113],"performance":[115],"results":[116],"show":[117],"effectiveness":[119],"our":[121],"proposed":[122],"model.":[123]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}