{"id":"https://openalex.org/W3186050523","doi":"https://doi.org/10.1109/waspaa52581.2021.9632775","title":"Joint Direction and Proximity Classification of Overlapping Sound Events from Binaural Audio","display_name":"Joint Direction and Proximity Classification of Overlapping Sound Events from Binaural Audio","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3186050523","doi":"https://doi.org/10.1109/waspaa52581.2021.9632775","mag":"3186050523"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa52581.2021.9632775","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa52581.2021.9632775","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},"type":"preprint","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/A5025199613","display_name":"Daniel Krause","orcid":"https://orcid.org/0000-0003-2704-636X"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Daniel Aleksander Krause","raw_affiliation_strings":["Faculty of Information Technology and Communication Sciences, Tampere University, Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology and Communication Sciences, Tampere University, Tampere, Finland","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010846139","display_name":"Archontis Politis","orcid":"https://orcid.org/0000-0002-0595-2356"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Archontis Politis","raw_affiliation_strings":["Faculty of Information Technology and Communication Sciences, Tampere University, Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology and Communication Sciences, Tampere University, Tampere, Finland","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079981416","display_name":"Annamaria Mesaros","orcid":"https://orcid.org/0000-0002-6640-9752"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Annamaria Mesaros","raw_affiliation_strings":["Faculty of Information Technology and Communication Sciences, Tampere University, Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology and Communication Sciences, Tampere University, Tampere, Finland","institution_ids":["https://openalex.org/I166825849"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5025199613"],"corresponding_institution_ids":["https://openalex.org/I166825849"],"apc_list":null,"apc_paid":null,"fwci":0.7715,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.70963428,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"331","last_page":"335"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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":0.9995999932289124,"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":0.998199999332428,"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":0.9929999709129333,"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/binaural-recording","display_name":"Binaural recording","score":0.9240174293518066},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8022776246070862},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.6988503336906433},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5542895197868347},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5468671917915344},{"id":"https://openalex.org/keywords/acoustic-source-localization","display_name":"Acoustic source localization","score":0.5192768573760986},{"id":"https://openalex.org/keywords/sound-localization","display_name":"Sound localization","score":0.506060779094696},{"id":"https://openalex.org/keywords/direction-of-arrival","display_name":"Direction of arrival","score":0.4904882609844208},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.43400394916534424},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.42865562438964844},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37181752920150757},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.32404130697250366},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11287248134613037},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06565570831298828}],"concepts":[{"id":"https://openalex.org/C201247586","wikidata":"https://www.wikidata.org/wiki/Q5612967","display_name":"Binaural recording","level":2,"score":0.9240174293518066},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8022776246070862},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.6988503336906433},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5542895197868347},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5468671917915344},{"id":"https://openalex.org/C93240960","wikidata":"https://www.wikidata.org/wiki/Q217270","display_name":"Acoustic source localization","level":3,"score":0.5192768573760986},{"id":"https://openalex.org/C68236139","wikidata":"https://www.wikidata.org/wiki/Q765652","display_name":"Sound localization","level":2,"score":0.506060779094696},{"id":"https://openalex.org/C172051844","wikidata":"https://www.wikidata.org/wiki/Q5280438","display_name":"Direction of arrival","level":3,"score":0.4904882609844208},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.43400394916534424},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.42865562438964844},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37181752920150757},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.32404130697250366},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11287248134613037},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06565570831298828},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems 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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/waspaa52581.2021.9632775","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa52581.2021.9632775","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},{"id":"pmh:oai:trepo.tuni.fi:10024/221234","is_oa":false,"landing_page_url":"https://trepo.tuni.fi/handle/10024/221234","pdf_url":null,"source":{"id":"https://openalex.org/S7407055260","display_name":"Trepo - Institutional Repository of Tampere University","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2360061192","display_name":"Teaching machines to listen","funder_award_id":"332063","funder_id":"https://openalex.org/F4320321108","funder_display_name":"Academy of Finland"},{"id":"https://openalex.org/G4923903852","display_name":null,"funder_award_id":"332063","funder_id":"https://openalex.org/F4320321108","funder_display_name":"Academy of Finland"}],"funders":[{"id":"https://openalex.org/F4320321108","display_name":"Academy of Finland","ror":"https://ror.org/05k73zm37"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W102482883","https://openalex.org/W1515932869","https://openalex.org/W1581848821","https://openalex.org/W2022347952","https://openalex.org/W2033526388","https://openalex.org/W2044063703","https://openalex.org/W2058497647","https://openalex.org/W2100668143","https://openalex.org/W2117678320","https://openalex.org/W2121356515","https://openalex.org/W2137666850","https://openalex.org/W2334833135","https://openalex.org/W2490695385","https://openalex.org/W2523246573","https://openalex.org/W2617440445","https://openalex.org/W2775505379","https://openalex.org/W2801757532","https://openalex.org/W2810934215","https://openalex.org/W2892163332","https://openalex.org/W2899564885","https://openalex.org/W2918022041","https://openalex.org/W2921741089","https://openalex.org/W2931658998","https://openalex.org/W2936437246","https://openalex.org/W2959539607","https://openalex.org/W2971670255","https://openalex.org/W2982102024","https://openalex.org/W3009927332","https://openalex.org/W3018444344","https://openalex.org/W3113688134","https://openalex.org/W3124180505","https://openalex.org/W4206633762","https://openalex.org/W4249052411","https://openalex.org/W4394669361","https://openalex.org/W6747331233"],"related_works":["https://openalex.org/W1991848873","https://openalex.org/W3004570917","https://openalex.org/W4389240440","https://openalex.org/W2084430325","https://openalex.org/W2041661331","https://openalex.org/W2539207221","https://openalex.org/W2045803470","https://openalex.org/W2242743481","https://openalex.org/W2809056180","https://openalex.org/W2015890751"],"abstract_inverted_index":{"Sound":[0],"source":[1],"proximity":[2,57,125],"and":[3,58,126,140],"distance":[4],"estimation":[5,60,128],"are":[6,147],"of":[7,41,54,79,86,99,122,142,156],"great":[8],"interest":[9],"in":[10,93],"many":[11],"practical":[12],"applications,":[13],"since":[14],"they":[15],"provide":[16],"significant":[17],"information":[18,112,136],"for":[19,37,149],"acoustic":[20],"scene":[21],"analysis.":[22],"As":[23],"both":[24,64],"tasks":[25],"share":[26],"complementary":[27],"qualities,":[28],"ensuring":[29],"efficient":[30],"interaction":[31],"between":[32],"these":[33],"two":[34,84,159],"is":[35],"crucial":[36],"a":[38,97,131,150],"complete":[39],"picture":[40],"an":[42],"aural":[43],"environment.":[44],"In":[45],"this":[46],"paper,":[47],"we":[48,82,105,118],"aim":[49],"to":[50,95,110,158],"investigate":[51],"several":[52],"ways":[53,121],"performing":[55],"joint":[56,132],"direction":[59,127],"from":[61],"binaural":[62,80,153],"recordings,":[63],"defined":[65],"as":[66],"coarse":[67],"classification":[68],"problems":[69,129],"based":[70],"on":[71],"Deep":[72],"Neural":[73],"Networks":[74],"(DNNs).":[75],"Considering":[76],"the":[77,88,114,124,138,143],"limitations":[78],"audio,":[81],"propose":[83,119],"methods":[85],"splitting":[87],"sphere":[89],"into":[90,130],"angular":[91],"areas":[92],"order":[94],"obtain":[96],"set":[98],"directional":[100],"classes.":[101],"For":[102],"each":[103],"method":[104],"study":[106],"different":[107],"model":[108],"types":[109],"acquire":[111],"about":[113,137],"direction-of-arrival":[115],"(DoA).":[116],"Finally,":[117],"various":[120],"combining":[123],"task":[133],"providing":[134],"temporal":[135],"onsets":[139],"offsets":[141],"appearing":[144],"sources.":[145],"Experiments":[146],"performed":[148],"synthetic":[151],"reverberant":[152],"dataset":[154],"consisting":[155],"up":[157],"overlapping":[160],"sound":[161],"events.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}
