{"id":"https://openalex.org/W3005741390","doi":"https://doi.org/10.1109/icassp40776.2020.9053045","title":"A Sequence Matching Network for Polyphonic Sound Event Localization and Detection","display_name":"A Sequence Matching Network for Polyphonic Sound Event Localization and Detection","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3005741390","doi":"https://doi.org/10.1109/icassp40776.2020.9053045","mag":"3005741390"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053045","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053045","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":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2002.05865","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039913415","display_name":"Thi Ngoc Tho Nguyen","orcid":"https://orcid.org/0000-0002-0210-6373"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Thi Ngoc Tho Nguyen","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105462806","display_name":"Douglas L. Jones","orcid":"https://orcid.org/0000-0002-7817-7629"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Douglas L. Jones","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, IL, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, IL, United States","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072584895","display_name":"Woon\u2010Seng Gan","orcid":"https://orcid.org/0000-0002-7143-1823"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Woon-Seng Gan","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":45,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"71","last_page":"75"},"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":0.9997000098228455,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.992900013923645,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7085072994232178},{"id":"https://openalex.org/keywords/direction-of-arrival","display_name":"Direction of arrival","score":0.6917828917503357},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6629799604415894},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.5860976576805115},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5340769290924072},{"id":"https://openalex.org/keywords/arrival-time","display_name":"Arrival time","score":0.46867284178733826},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.46845412254333496},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.45315149426460266},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.4523214101791382},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.43276745080947876},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42702239751815796},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4071948230266571},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.18999341130256653},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10535544157028198},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08720865845680237},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08340892195701599},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07198470830917358}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7085072994232178},{"id":"https://openalex.org/C172051844","wikidata":"https://www.wikidata.org/wiki/Q5280438","display_name":"Direction of arrival","level":3,"score":0.6917828917503357},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6629799604415894},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.5860976576805115},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5340769290924072},{"id":"https://openalex.org/C3017552255","wikidata":"https://www.wikidata.org/wiki/Q4135208","display_name":"Arrival time","level":2,"score":0.46867284178733826},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.46845412254333496},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.45315149426460266},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.4523214101791382},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.43276745080947876},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42702239751815796},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4071948230266571},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.18999341130256653},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10535544157028198},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08720865845680237},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08340892195701599},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07198470830917358},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C22212356","wikidata":"https://www.wikidata.org/wiki/Q775325","display_name":"Transport engineering","level":1,"score":0.0},{"id":"https://openalex.org/C21822782","wikidata":"https://www.wikidata.org/wiki/Q131214","display_name":"Antenna (radio)","level":2,"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":2,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053045","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053045","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"},{"id":"pmh:oai:arXiv.org:2002.05865","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2002.05865","pdf_url":"https://arxiv.org/pdf/2002.05865","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2002.05865","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2002.05865","pdf_url":"https://arxiv.org/pdf/2002.05865","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1422086691","https://openalex.org/W1511569476","https://openalex.org/W1603075283","https://openalex.org/W1964998538","https://openalex.org/W1993678034","https://openalex.org/W2066218102","https://openalex.org/W2110059230","https://openalex.org/W2113638573","https://openalex.org/W2139129402","https://openalex.org/W2292996718","https://openalex.org/W2341412280","https://openalex.org/W2408239454","https://openalex.org/W2509065397","https://openalex.org/W2511089602","https://openalex.org/W2518102674","https://openalex.org/W2591013610","https://openalex.org/W2747685395","https://openalex.org/W2759976799","https://openalex.org/W2810934215","https://openalex.org/W2914312680","https://openalex.org/W2942551338","https://openalex.org/W2963099423","https://openalex.org/W2964342924","https://openalex.org/W2982382207","https://openalex.org/W2982429715","https://openalex.org/W2998508940","https://openalex.org/W3098357269","https://openalex.org/W3098454764","https://openalex.org/W6628353819","https://openalex.org/W6630427285","https://openalex.org/W6743440100","https://openalex.org/W6922472746"],"related_works":["https://openalex.org/W2411659965","https://openalex.org/W3150350962","https://openalex.org/W2539149779","https://openalex.org/W3145715554","https://openalex.org/W2895890781","https://openalex.org/W4300440044","https://openalex.org/W3142818024","https://openalex.org/W2357430309","https://openalex.org/W2544718067","https://openalex.org/W19682173"],"abstract_inverted_index":{"Polyphonic":[0],"sound":[1,15,41,70,84,141,154],"event":[2,16,42,71,116,142,155],"detection":[3,17,43,72,145,158],"and":[4,44,47,73,86,118,124,134,144,157],"direction-of-arrival":[5,23,45,120],"estimation":[6,24,75],"require":[7],"different":[8],"input":[9,38],"features":[10,39],"from":[11],"audio":[12],"signals.":[13],"While":[14],"mainly":[18],"relies":[19,25],"on":[20,26],"time-frequency":[21],"patterns,":[22],"magnitude":[27],"or":[28,53],"phase":[29],"differences":[30],"between":[31],"microphones.":[32],"Previous":[33],"approaches":[34],"use":[35],"the":[36,49,66,69,78,83,88,93,99,110,115,119,128,131,136,139,151,166],"same":[37],"for":[40],"estimation,":[46],"train":[48,103],"two":[50,111],"tasks":[51],"jointly":[52],"in":[54,130],"a":[55,61,104],"two-stage":[56],"transfer-learning":[57],"manner.":[58],"We":[59],"propose":[60],"two-step":[62],"approach":[63,126],"that":[64],"decouples":[65],"learning":[67],"of":[68,95,114,138],"directional-of-arrival":[74],"systems.":[76],"In":[77,98],"first":[79],"step,":[80,101],"we":[81,102],"detect":[82],"events":[85],"estimate":[87],"directions-of-arrival":[89],"separately":[90],"to":[91,108,165],"optimize":[92],"performance":[94,137,163],"each":[96],"system.":[97,146],"second":[100],"deep":[105],"neural":[106],"network":[107],"match":[109],"output":[112],"sequences":[113],"detector":[117],"estimator.":[121],"This":[122],"modular":[123],"hierarchical":[125],"allows":[127],"flexibility":[129],"system":[132],"design,":[133],"increase":[135],"whole":[140],"localization":[143,156],"The":[147],"experimental":[148],"results":[149],"using":[150],"DCASE":[152],"2019":[153],"dataset":[159],"show":[160],"an":[161],"improved":[162],"compared":[164],"previous":[167],"state-of-the-art":[168],"solutions.":[169]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
