{"id":"https://openalex.org/W3144042318","doi":"https://doi.org/10.1109/ieeeconf49454.2021.9382730","title":"Multi-channel Environmental Sound Segmentation utilizing Sound Source Localization and Separation U-Net","display_name":"Multi-channel Environmental Sound Segmentation utilizing Sound Source Localization and Separation U-Net","publication_year":2021,"publication_date":"2021-01-11","ids":{"openalex":"https://openalex.org/W3144042318","doi":"https://doi.org/10.1109/ieeeconf49454.2021.9382730","mag":"3144042318"},"language":"en","primary_location":{"id":"doi:10.1109/ieeeconf49454.2021.9382730","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieeeconf49454.2021.9382730","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/SICE International Symposium on System Integration (SII)","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/A5091425252","display_name":"Yui Sudo","orcid":"https://orcid.org/0000-0003-2094-6701"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yui Sudo","raw_affiliation_strings":["Department of Systems and Control Engineering, School of Engineering, Tokyo Institute of Technology, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Systems and Control Engineering, School of Engineering, Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003325000","display_name":"Katsutoshi Itoyama","orcid":"https://orcid.org/0000-0002-7098-3896"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Katsutoshi Itoyama","raw_affiliation_strings":["Department of Systems and Control Engineering, School of Engineering, Tokyo Institute of Technology, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Systems and Control Engineering, School of Engineering, Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068958993","display_name":"Kenji Nishida","orcid":"https://orcid.org/0000-0003-4214-4005"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kenji Nishida","raw_affiliation_strings":["Department of Systems and Control Engineering, School of Engineering, Tokyo Institute of Technology, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Systems and Control Engineering, School of Engineering, Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091708408","display_name":"Kazuhiro Nakadai","orcid":"https://orcid.org/0000-0002-6134-4558"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]},{"id":"https://openalex.org/I1283473643","display_name":"Honda (Japan)","ror":"https://ror.org/03jzay846","country_code":"JP","type":"company","lineage":["https://openalex.org/I1283473643"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuhiro Nakadai","raw_affiliation_strings":["Department of Systems and Control Engineering, School of Engineering, Tokyo Institute of Technology, Tokyo, Japan","Honda Research Institute Japan Co., Ltd, Saitama, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Systems and Control Engineering, School of Engineering, Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"Honda Research Institute Japan Co., Ltd, Saitama, Japan","institution_ids":["https://openalex.org/I1283473643"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5091425252"],"corresponding_institution_ids":["https://openalex.org/I114531698"],"apc_list":null,"apc_paid":null,"fwci":1.0665,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.75929682,"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/T10860","display_name":"Speech 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/T10860","display_name":"Speech 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/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"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":0.9898999929428101,"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":0.7004177570343018},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5721777677536011},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5293532013893127},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.520435631275177},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.49993133544921875},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.4830816090106964},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4771668016910553},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4567384421825409},{"id":"https://openalex.org/keywords/acoustic-source-localization","display_name":"Acoustic source localization","score":0.4407684803009033},{"id":"https://openalex.org/keywords/direction-of-arrival","display_name":"Direction of arrival","score":0.43260452151298523},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.42531150579452515},{"id":"https://openalex.org/keywords/environmental-noise","display_name":"Environmental noise","score":0.42271941900253296},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4221288859844208},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.37920212745666504},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2859764099121094},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09600427746772766}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7004177570343018},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5721777677536011},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5293532013893127},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.520435631275177},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.49993133544921875},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.4830816090106964},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4771668016910553},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4567384421825409},{"id":"https://openalex.org/C93240960","wikidata":"https://www.wikidata.org/wiki/Q217270","display_name":"Acoustic source localization","level":3,"score":0.4407684803009033},{"id":"https://openalex.org/C172051844","wikidata":"https://www.wikidata.org/wiki/Q5280438","display_name":"Direction of arrival","level":3,"score":0.43260452151298523},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.42531150579452515},{"id":"https://openalex.org/C86781634","wikidata":"https://www.wikidata.org/wiki/Q2478325","display_name":"Environmental noise","level":3,"score":0.42271941900253296},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4221288859844208},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.37920212745666504},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2859764099121094},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09600427746772766},{"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/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/ieeeconf49454.2021.9382730","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieeeconf49454.2021.9382730","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/SICE International Symposium on System Integration (SII)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W199515402","https://openalex.org/W1522301498","https://openalex.org/W1560213421","https://openalex.org/W2075916569","https://openalex.org/W2086384421","https://openalex.org/W2097117768","https://openalex.org/W2113638573","https://openalex.org/W2122796820","https://openalex.org/W2160911448","https://openalex.org/W2460742184","https://openalex.org/W2561787614","https://openalex.org/W2591013610","https://openalex.org/W2594166949","https://openalex.org/W2742299865","https://openalex.org/W2765218824","https://openalex.org/W2774707525","https://openalex.org/W2803322398","https://openalex.org/W2888954542","https://openalex.org/W2889442120","https://openalex.org/W2889503488","https://openalex.org/W2892163332","https://openalex.org/W2933305660","https://openalex.org/W2963679447","https://openalex.org/W2963773971","https://openalex.org/W2964121744","https://openalex.org/W2964309882","https://openalex.org/W2982429715","https://openalex.org/W2982604633","https://openalex.org/W2998657200","https://openalex.org/W3003322464","https://openalex.org/W3005741390","https://openalex.org/W3008762051","https://openalex.org/W3012130433","https://openalex.org/W3092565258","https://openalex.org/W6608016876","https://openalex.org/W6631190155","https://openalex.org/W6746914816","https://openalex.org/W6769845053","https://openalex.org/W6773738941","https://openalex.org/W6922472746"],"related_works":["https://openalex.org/W1608003482","https://openalex.org/W2809543295","https://openalex.org/W2903040254","https://openalex.org/W2042926344","https://openalex.org/W2768802724","https://openalex.org/W2074134755","https://openalex.org/W2350404734","https://openalex.org/W4226449293","https://openalex.org/W2943743938","https://openalex.org/W2794792329"],"abstract_inverted_index":{"This":[0,120,150],"paper":[1,121],"proposes":[2,122],"a":[3],"multi-channel":[4,123],"environmental":[5,110,124,173],"sound":[6,10,19,22,56,60,125,134,138],"segmentation":[7,11,126],"method.":[8,193],"Environmental":[9],"is":[12,106],"an":[13],"integrated":[14],"method":[15,127,151,185],"that":[16,128,176,189],"deals":[17],"with":[18],"source":[20,23,57,61,135,139],"localization,":[21],"separation":[24,41,62],"and":[25,59,66,89,137,141,162],"class":[26,67],"identification.":[27],"When":[28],"multiple":[29],"microphones":[30],"are":[31,72],"available,":[32],"spatial":[33,64],"features":[34,65,71],"can":[35],"be":[36,103],"used":[37,98],"to":[38,81,113,154],"improve":[39],"the":[40,75,82,85,90,94,114,147,155,158,163,168,177,183,191],"accuracy":[42],"of":[43,87,117,160,182,190],"signals":[44],"from":[45],"different":[46],"directions;":[47],"however,":[48],"conventional":[49,192],"methods":[50],"have":[51],"two":[52],"drawbacks:":[53],"(a)":[54],"Since":[55],"localization":[58,136],"using":[63,69,167],"identification":[68],"spectral":[70],"trained":[73],"in":[74,99],"same":[76],"neural":[77,143],"network,":[78],"it":[79,105],"overfits":[80],"relationship":[83,156],"between":[84,157],"direction":[86,159],"arrival":[88,161],"class.":[91,164],"(b)":[92],"Although":[93],"permutation":[95],"invariant":[96],"training":[97],"speech":[100],"recognition":[101],"could":[102],"extended,":[104],"not":[107],"practical":[108],"for":[109],"sounds":[111,174],"due":[112],"maximum":[115],"number":[116],"speakers":[118],"limitation.":[119],"combines":[129],"U-Net":[130],"which":[131,145],"simultaneously":[132],"performs":[133],"separation,":[140],"convolutional":[142],"network":[144],"classifies":[146],"separated":[148],"sounds.":[149],"prevents":[152],"overfitting":[153],"Simulation":[165],"experiments":[166],"created":[169],"datasets":[170],"including":[171],"75-class":[172],"showed":[175],"root":[178],"mean":[179],"squared":[180],"error":[181],"proposed":[184],"was":[186],"lower":[187],"than":[188]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"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"}