{"id":"https://openalex.org/W3116084609","doi":"https://doi.org/10.23919/eusipco47968.2020.9287224","title":"Exploiting Attention-based Sequence-to-Sequence Architectures for Sound Event Localization","display_name":"Exploiting Attention-based Sequence-to-Sequence Architectures for Sound Event Localization","publication_year":2020,"publication_date":"2020-12-18","ids":{"openalex":"https://openalex.org/W3116084609","doi":"https://doi.org/10.23919/eusipco47968.2020.9287224","mag":"3116084609"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco47968.2020.9287224","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco47968.2020.9287224","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 28th European Signal Processing Conference (EUSIPCO)","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/A5035233948","display_name":"Christopher Schymura","orcid":"https://orcid.org/0000-0002-6128-3556"},"institutions":[{"id":"https://openalex.org/I904495901","display_name":"Ruhr University Bochum","ror":"https://ror.org/04tsk2644","country_code":"DE","type":"education","lineage":["https://openalex.org/I904495901"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christopher Schymura","raw_affiliation_strings":["Institute of Communication Acoustics, Ruhr University Bochum, Bochum, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Communication Acoustics, Ruhr University Bochum, Bochum, Germany","institution_ids":["https://openalex.org/I904495901"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070624983","display_name":"Tsubasa Ochiai","orcid":"https://orcid.org/0000-0002-2519-2032"},"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":"Tsubasa Ochiai","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023868166","display_name":"Marc Delcroix","orcid":"https://orcid.org/0000-0002-5175-7834"},"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":"Marc Delcroix","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069398831","display_name":"Keisuke Kinoshita","orcid":"https://orcid.org/0009-0008-7987-8188"},"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":"Keisuke Kinoshita","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021240106","display_name":"Tomohiro Nakatani","orcid":"https://orcid.org/0000-0002-7487-7150"},"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":"Tomohiro Nakatani","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009309584","display_name":"Shoko Araki","orcid":"https://orcid.org/0000-0003-4363-4305"},"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":"Shoko Araki","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007017640","display_name":"Dorothea Kolossa","orcid":"https://orcid.org/0000-0003-0678-3053"},"institutions":[{"id":"https://openalex.org/I904495901","display_name":"Ruhr University Bochum","ror":"https://ror.org/04tsk2644","country_code":"DE","type":"education","lineage":["https://openalex.org/I904495901"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dorothea Kolossa","raw_affiliation_strings":["Institute of Communication Acoustics, Ruhr University Bochum, Bochum, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Communication Acoustics, Ruhr University Bochum, Bochum, Germany","institution_ids":["https://openalex.org/I904495901"]}]}],"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":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"231","last_page":"235"},"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":0.9991000294685364,"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":0.9976000189781189,"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":0.7923142910003662},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.677484393119812},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6519160270690918},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.6115877032279968},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.5357811450958252},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.513155996799469},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.45904794335365295},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4211300313472748},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42101845145225525},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4167799651622772},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.4167681336402893},{"id":"https://openalex.org/keywords/direction-of-arrival","display_name":"Direction of arrival","score":0.413900226354599},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4072072505950928},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35983526706695557},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.17686131596565247},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.0990736186504364},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0822494626045227},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07605186104774475}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7923142910003662},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.677484393119812},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6519160270690918},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.6115877032279968},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.5357811450958252},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.513155996799469},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.45904794335365295},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4211300313472748},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42101845145225525},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4167799651622772},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.4167681336402893},{"id":"https://openalex.org/C172051844","wikidata":"https://www.wikidata.org/wiki/Q5280438","display_name":"Direction of arrival","level":3,"score":0.413900226354599},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4072072505950928},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35983526706695557},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.17686131596565247},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0990736186504364},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0822494626045227},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07605186104774475},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/eusipco47968.2020.9287224","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco47968.2020.9287224","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 28th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5799999833106995,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1555217905","https://openalex.org/W1677182931","https://openalex.org/W1972978214","https://openalex.org/W2113638573","https://openalex.org/W2130989868","https://openalex.org/W2131774270","https://openalex.org/W2133564696","https://openalex.org/W2148229831","https://openalex.org/W2168745915","https://openalex.org/W2222512263","https://openalex.org/W2460742184","https://openalex.org/W2611943505","https://openalex.org/W2772736377","https://openalex.org/W2772956764","https://openalex.org/W2800100150","https://openalex.org/W2807015669","https://openalex.org/W2810934215","https://openalex.org/W2888793942","https://openalex.org/W2900582271","https://openalex.org/W2908510526","https://openalex.org/W2931658998","https://openalex.org/W2941761746","https://openalex.org/W2963403868","https://openalex.org/W2964308564","https://openalex.org/W2964342924","https://openalex.org/W2970971581","https://openalex.org/W2972837679","https://openalex.org/W2982341288","https://openalex.org/W3102937397","https://openalex.org/W3104757150","https://openalex.org/W3105684258","https://openalex.org/W3124180505","https://openalex.org/W4229977739","https://openalex.org/W4295312788","https://openalex.org/W4385245566","https://openalex.org/W6679434410","https://openalex.org/W6739901393","https://openalex.org/W6757817989","https://openalex.org/W6766978945","https://openalex.org/W6785829207"],"related_works":["https://openalex.org/W2009811519","https://openalex.org/W2489043436","https://openalex.org/W2289868279","https://openalex.org/W4231351862","https://openalex.org/W4292261062","https://openalex.org/W4212794605","https://openalex.org/W4315836293","https://openalex.org/W4243888788","https://openalex.org/W3004352674","https://openalex.org/W2969585518"],"abstract_inverted_index":{"Sound":[0],"event":[1,52,144],"localization":[2,53,149],"frameworks":[3],"based":[4],"on":[5,114,137],"deep":[6],"neural":[7],"networks":[8],"have":[9,64],"shown":[10],"increased":[11],"robustness":[12],"with":[13],"respect":[14],"to":[15,21,38,50,68,87,95,152],"reverberation":[16],"and":[17,74,124,158],"noise":[18],"in":[19,70,108,155],"comparison":[20],"classical":[22],"parametric":[23],"approaches.":[24],"In":[25,78],"particular,":[26],"recurrent":[27],"architectures":[28],"that":[29,117],"incorporate":[30],"temporal":[31,106],"context":[32],"into":[33],"the":[34,109,122,130],"estimation":[35],"process":[36],"seem":[37],"be":[39],"well-suited":[40],"for":[41,104,120,142],"this":[42,79],"task.":[43],"This":[44],"paper":[45],"proposes":[46],"a":[47,81,88,96],"novel":[48],"approach":[49],"sound":[51,127,143],"by":[54,112],"utilizing":[55],"an":[56],"attention-based":[57],"sequence-to-sequence":[58],"model.":[59],"These":[60],"types":[61],"of":[62,98,126],"models":[63],"been":[65],"successfully":[66],"applied":[67],"problems":[69],"natural":[71],"language":[72],"processing":[73],"automatic":[75],"speech":[76],"recognition.":[77],"work,":[80],"multi-channel":[82],"audio":[83,110],"signal":[84,111],"is":[85,92,135],"encoded":[86],"latent":[89],"representation,":[90],"which":[91],"subsequently":[93],"decoded":[94],"sequence":[97],"estimated":[99],"directions-of-arrival.":[100],"Herein,":[101],"attentions":[102],"allow":[103],"capturing":[105],"dependencies":[107],"focusing":[113],"specific":[115],"frames":[116],"are":[118],"relevant":[119],"estimating":[121],"activity":[123],"direction-of-arrival":[125],"events":[128],"at":[129],"current":[131],"time-step.":[132],"The":[133],"framework":[134],"evaluated":[136],"three":[138],"publicly":[139],"available":[140],"datasets":[141],"localization.":[145],"It":[146],"yields":[147],"superior":[148],"performance":[150],"compared":[151],"state-of-the-art":[153],"methods":[154],"both":[156],"anechoic":[157],"reverberant":[159],"conditions.":[160]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}