{"id":"https://openalex.org/W4221146826","doi":"https://doi.org/10.1109/icassp43922.2022.9747603","title":"Echo-Aware Adaptation of Sound Event Localization and Detection in Unknown Environments","display_name":"Echo-Aware Adaptation of Sound Event Localization and Detection in Unknown Environments","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4221146826","doi":"https://doi.org/10.1109/icassp43922.2022.9747603"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747603","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747603","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5017806490","display_name":"Masahiro Yasuda","orcid":"https://orcid.org/0000-0002-8384-8167"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masahiro Yasuda","raw_affiliation_strings":["NTT Corporation,Japan","NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062509967","display_name":"Yasunori Ohishi","orcid":"https://orcid.org/0000-0002-7856-248X"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yasunori Ohishi","raw_affiliation_strings":["NTT Corporation,Japan","NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108799515","display_name":"Shoichiro Saito","orcid":"https://orcid.org/0000-0002-8712-0464"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shoichiro Saito","raw_affiliation_strings":["NTT Corporation,Japan","NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":3.1377,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.93494705,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"226","last_page":"230"},"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":0.9998000264167786,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/computer-science","display_name":"Computer science","score":0.7108194231987},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.6857612133026123},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5764732956886292},{"id":"https://openalex.org/keywords/echo","display_name":"Echo (communications protocol)","score":0.4541144371032715},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.44845128059387207},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4474294185638428},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.43806225061416626},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.43090352416038513},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4165511727333069},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4148828983306885},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3652888536453247},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2471030056476593},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.0964168906211853},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.09119284152984619},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07505279779434204}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7108194231987},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.6857612133026123},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5764732956886292},{"id":"https://openalex.org/C2779426996","wikidata":"https://www.wikidata.org/wiki/Q18389128","display_name":"Echo (communications protocol)","level":2,"score":0.4541144371032715},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.44845128059387207},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4474294185638428},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.43806225061416626},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.43090352416038513},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4165511727333069},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4148828983306885},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3652888536453247},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2471030056476593},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0964168906211853},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.09119284152984619},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07505279779434204},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747603","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747603","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7099999785423279,"id":"https://metadata.un.org/sdg/15","display_name":"Life in Land"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1882958252","https://openalex.org/W2024787486","https://openalex.org/W2051145414","https://openalex.org/W2072604753","https://openalex.org/W2157331557","https://openalex.org/W2187089797","https://openalex.org/W2204091679","https://openalex.org/W2292996718","https://openalex.org/W2511089602","https://openalex.org/W2663904211","https://openalex.org/W2751116311","https://openalex.org/W2883787264","https://openalex.org/W2937324313","https://openalex.org/W2964342924","https://openalex.org/W2982382207","https://openalex.org/W2982429715","https://openalex.org/W2997076748","https://openalex.org/W2998139081","https://openalex.org/W3015469592","https://openalex.org/W3108655859","https://openalex.org/W3163193264","https://openalex.org/W4287070075","https://openalex.org/W4287120192","https://openalex.org/W4287766186","https://openalex.org/W6631190155","https://openalex.org/W6639480849","https://openalex.org/W6743647910","https://openalex.org/W6776723300","https://openalex.org/W6779923105","https://openalex.org/W6796679619","https://openalex.org/W6798133626"],"related_works":["https://openalex.org/W1656519308","https://openalex.org/W2042717753","https://openalex.org/W2022849831","https://openalex.org/W2037265366","https://openalex.org/W2026603686","https://openalex.org/W2331622705","https://openalex.org/W2391832549","https://openalex.org/W4401069787","https://openalex.org/W2348192562","https://openalex.org/W2073125797"],"abstract_inverted_index":{"Our":[0],"goal":[1],"is":[2,27,73],"to":[3,34,80,131],"develop":[4],"a":[5,84],"sound":[6],"event":[7],"localization":[8],"and":[9,40],"detection":[10],"(SELD)":[11],"system":[12,21,69],"that":[13,55,140],"works":[14],"robustly":[15],"in":[16,29,44,66,147],"unknown":[17,31,81,113,148],"environments.":[18,149],"A":[19],"SELD":[20,145],"trained":[22],"on":[23,50,63,137],"known":[24],"environment":[25,32,65,114],"data":[26,62],"degraded":[28],"an":[30,121],"due":[33],"environmental":[35,100],"effects":[36,101],"such":[37],"as":[38],"reverberation":[39],"noise":[41],"not":[42],"contained":[43],"the":[45,64,68,103,112,133,141],"training":[46],"data.":[47],"Previous":[48],"studies":[49],"related":[51],"tasks":[52],"have":[53],"shown":[54],"domain":[56],"adaptation":[57,79],"methods":[58],"are":[59],"effective":[60],"when":[61],"which":[67,98],"will":[70],"be":[71],"used":[72],"available":[74],"even":[75],"without":[76],"labels.":[77],"However":[78],"environments":[82],"remains":[83],"difficult":[85],"task.":[86],"In":[87],"this":[88],"study,":[89],"we":[90],"propose":[91],"echo-aware":[92],"feature":[93,104],"refinement":[94],"(EAR)":[95],"for":[96],"SELD,":[97],"suppresses":[99],"at":[102],"level":[105],"by":[106],"using":[107],"additional":[108],"spatial":[109],"cues":[110],"of":[111],"obtained":[115],"through":[116],"measuring":[117],"acoustic":[118],"echoes.":[119],"FOA-MEIR1,":[120],"impulse":[122],"response":[123],"dataset":[124],"containing":[125],"over":[126],"100":[127],"environments,":[128],"was":[129],"recorded":[130],"validate":[132],"proposed":[134],"method.":[135],"Experiments":[136],"FOA-MEIR":[138],"show":[139],"EAR":[142],"effectively":[143],"improves":[144],"performance":[146]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":7}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}