{"id":"https://openalex.org/W3006405238","doi":"https://doi.org/10.1109/icassp40776.2020.9054462","title":"Sound Event Localization Based on Sound Intensity Vector Refined by Dnn-Based Denoising and Source Separation","display_name":"Sound Event Localization Based on Sound Intensity Vector Refined by Dnn-Based Denoising and Source Separation","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3006405238","doi":"https://doi.org/10.1109/icassp40776.2020.9054462","mag":"3006405238"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054462","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054462","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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2002.05994","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017806490","display_name":"Masahiro Yasuda","orcid":"https://orcid.org/0000-0002-8384-8167"},"institutions":[{"id":"https://openalex.org/I135768898","display_name":"Ritsumeikan University","ror":"https://ror.org/0197nmd03","country_code":"JP","type":"education","lineage":["https://openalex.org/I135768898","https://openalex.org/I4390039241"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Masahiro Yasuda","raw_affiliation_strings":["Ritsumeikan University, Shiga, Japan","Ritsumeikan University, Shiga, JAPAN,"],"affiliations":[{"raw_affiliation_string":"Ritsumeikan University, Shiga, Japan","institution_ids":["https://openalex.org/I135768898"]},{"raw_affiliation_string":"Ritsumeikan University, Shiga, JAPAN,","institution_ids":["https://openalex.org/I135768898"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101503856","display_name":"Yuma Koizumi","orcid":"https://orcid.org/0000-0003-3645-6213"},"institutions":[{"id":"https://openalex.org/I135768898","display_name":"Ritsumeikan University","ror":"https://ror.org/0197nmd03","country_code":"JP","type":"education","lineage":["https://openalex.org/I135768898","https://openalex.org/I4390039241"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuma Koizumi","raw_affiliation_strings":["Ritsumeikan University, Shiga, Japan","Ritsumeikan University, Shiga, JAPAN,"],"affiliations":[{"raw_affiliation_string":"Ritsumeikan University, Shiga, Japan","institution_ids":["https://openalex.org/I135768898"]},{"raw_affiliation_string":"Ritsumeikan University, Shiga, JAPAN,","institution_ids":["https://openalex.org/I135768898"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108799515","display_name":"Shoichiro Saito","orcid":"https://orcid.org/0000-0002-8712-0464"},"institutions":[{"id":"https://openalex.org/I135768898","display_name":"Ritsumeikan University","ror":"https://ror.org/0197nmd03","country_code":"JP","type":"education","lineage":["https://openalex.org/I135768898","https://openalex.org/I4390039241"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shoichiro Saito","raw_affiliation_strings":["Ritsumeikan University, Shiga, Japan","Ritsumeikan University, Shiga, JAPAN,"],"affiliations":[{"raw_affiliation_string":"Ritsumeikan University, Shiga, Japan","institution_ids":["https://openalex.org/I135768898"]},{"raw_affiliation_string":"Ritsumeikan University, Shiga, JAPAN,","institution_ids":["https://openalex.org/I135768898"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112412633","display_name":"Hisashi Uematsu","orcid":null},"institutions":[{"id":"https://openalex.org/I135768898","display_name":"Ritsumeikan University","ror":"https://ror.org/0197nmd03","country_code":"JP","type":"education","lineage":["https://openalex.org/I135768898","https://openalex.org/I4390039241"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hisashi Uematsu","raw_affiliation_strings":["Ritsumeikan University, Shiga, Japan","Ritsumeikan University, Shiga, JAPAN,"],"affiliations":[{"raw_affiliation_string":"Ritsumeikan University, Shiga, Japan","institution_ids":["https://openalex.org/I135768898"]},{"raw_affiliation_string":"Ritsumeikan University, Shiga, JAPAN,","institution_ids":["https://openalex.org/I135768898"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009991655","display_name":"Keisuke Imoto","orcid":"https://orcid.org/0000-0002-0703-8293"},"institutions":[{"id":"https://openalex.org/I135768898","display_name":"Ritsumeikan University","ror":"https://ror.org/0197nmd03","country_code":"JP","type":"education","lineage":["https://openalex.org/I135768898","https://openalex.org/I4390039241"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keisuke Imoto","raw_affiliation_strings":["Ritsumeikan University, Shiga, Japan","Ritsumeikan University, Shiga, JAPAN,"],"affiliations":[{"raw_affiliation_string":"Ritsumeikan University, Shiga, Japan","institution_ids":["https://openalex.org/I135768898"]},{"raw_affiliation_string":"Ritsumeikan University, Shiga, JAPAN,","institution_ids":["https://openalex.org/I135768898"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5017806490"],"corresponding_institution_ids":["https://openalex.org/I135768898"],"apc_list":null,"apc_paid":null,"fwci":0.4571,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.59098345,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"651","last_page":"655"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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/T10860","display_name":"Speech 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/T11309","display_name":"Music and Audio Processing","score":0.9988999962806702,"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/T11665","display_name":"Animal Vocal Communication and Behavior","score":0.9873999953269958,"subfield":{"id":"https://openalex.org/subfields/1309","display_name":"Developmental Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.8064950704574585},{"id":"https://openalex.org/keywords/direction-of-arrival","display_name":"Direction of arrival","score":0.709152102470398},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6164655685424805},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.5764651298522949},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.507195234298706},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.505770206451416},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5044597387313843},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.48506060242652893},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.4794420301914215},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4410386085510254},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3954312205314636},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.11232167482376099},{"id":"https://openalex.org/keywords/sound-pressure","display_name":"Sound pressure","score":0.1089572012424469},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06203734874725342}],"concepts":[{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.8064950704574585},{"id":"https://openalex.org/C172051844","wikidata":"https://www.wikidata.org/wiki/Q5280438","display_name":"Direction of arrival","level":3,"score":0.709152102470398},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6164655685424805},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.5764651298522949},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.507195234298706},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.505770206451416},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5044597387313843},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.48506060242652893},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.4794420301914215},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4410386085510254},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3954312205314636},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.11232167482376099},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.1089572012424469},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06203734874725342},{"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":5,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054462","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054462","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:2002.05994","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2002.05994","pdf_url":"https://arxiv.org/pdf/2002.05994","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:3006405238","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2002.05994.pdf","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":"doi:10.48550/arxiv.2002.05994","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2002.05994","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"},{"id":"doi:10.17023/h6bh-hc47","is_oa":true,"landing_page_url":"https://doi.org/10.17023/h6bh-hc47","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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:2002.05994","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2002.05994","pdf_url":"https://arxiv.org/pdf/2002.05994","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":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W3006405238.pdf"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1605726227","https://openalex.org/W1987906574","https://openalex.org/W1993678034","https://openalex.org/W2113638573","https://openalex.org/W2149648624","https://openalex.org/W2204091679","https://openalex.org/W2734774145","https://openalex.org/W2745195618","https://openalex.org/W2751116311","https://openalex.org/W2805233667","https://openalex.org/W2810934215","https://openalex.org/W2883787264","https://openalex.org/W2897088495","https://openalex.org/W2897361856","https://openalex.org/W2917254586","https://openalex.org/W2945482470","https://openalex.org/W2964121744","https://openalex.org/W2964342924","https://openalex.org/W2982382207","https://openalex.org/W2982429715","https://openalex.org/W2982680886","https://openalex.org/W2998139081","https://openalex.org/W6631190155","https://openalex.org/W6636324218","https://openalex.org/W6682325752","https://openalex.org/W6743647910","https://openalex.org/W6922472746"],"related_works":["https://openalex.org/W2952502806","https://openalex.org/W3113264499","https://openalex.org/W567105040","https://openalex.org/W2994698073","https://openalex.org/W3015078117","https://openalex.org/W3094320653","https://openalex.org/W2068556767","https://openalex.org/W3092626288","https://openalex.org/W3212695225","https://openalex.org/W3016139178","https://openalex.org/W2719690335","https://openalex.org/W2187902288","https://openalex.org/W3211178721","https://openalex.org/W2980157024","https://openalex.org/W3172896385","https://openalex.org/W3155195349","https://openalex.org/W2966256366","https://openalex.org/W3157203004","https://openalex.org/W2978977033","https://openalex.org/W2491711464"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,19,33,74,113],"direction-of-arrival":[3],"(DOA)":[4],"estimation":[5,15,40,89,105,127],"method":[6,100,123],"for":[7,41,67,86,106],"Sound":[8],"Event":[9],"Localization":[10],"and":[11,43,78,96,109],"Detection":[12],"(SELD).":[13],"Direct":[14],"of":[16,56,76,133],"DOA":[17,39,88,104,126],"using":[18,112],"deep":[20],"neural":[21],"network":[22],"(DNN),":[23],"i.e.":[24],"completely-datadriven":[25],"approach,":[26],"achieves":[27,124],"high":[28],"accuracy.":[29],"However,":[30],"there":[31],"is":[32,59,65,90],"gap":[34],"in":[35],"the":[36,54,81,102,121,134],"accuracy":[37,55,128],"between":[38],"single":[42,108],"overlapping":[44,110],"sources":[45,111],"because":[46],"they":[47],"cannot":[48],"incorporate":[49],"physical":[50],"knowledge.":[51],"Meanwhile,":[52],"although":[53],"physics-based":[57,77,87],"approaches":[58],"inferior":[60],"to":[61],"DNN-based":[62,79,94],"approaches,":[63],"it":[64],"robust":[66],"overlapping-source.":[68],"In":[69],"this":[70],"study,":[71],"we":[72],"consider":[73],"combination":[75],"approaches;":[80],"sound":[82],"intensity":[83],"vectors":[84],"(IVs)":[85],"refined":[91],"based":[92],"on":[93,129],"denoising":[95],"source":[97],"separation.":[98],"This":[99],"enables":[101],"accurate":[103],"both":[107],"spherical":[114],"microphone":[115],"array.":[116],"Experimental":[117],"results":[118],"show":[119],"that":[120],"proposed":[122],"state-of-the-art":[125],"an":[130],"open":[131],"dataset":[132],"SELD.":[135]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-21T08:13:44.787528","created_date":"2022-02-24T00:00:00"}