{"id":"https://openalex.org/W3113688134","doi":"https://doi.org/10.23919/eusipco47968.2020.9287374","title":"Feature Overview for Joint Modeling of Sound Event Detection and Localization Using a Microphone Array","display_name":"Feature Overview for Joint Modeling of Sound Event Detection and Localization Using a Microphone Array","publication_year":2020,"publication_date":"2020-12-18","ids":{"openalex":"https://openalex.org/W3113688134","doi":"https://doi.org/10.23919/eusipco47968.2020.9287374","mag":"3113688134"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco47968.2020.9287374","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco47968.2020.9287374","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":"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/A5025199613","display_name":"Daniel Krause","orcid":"https://orcid.org/0000-0003-2704-636X"},"institutions":[{"id":"https://openalex.org/I686019","display_name":"AGH University of Krakow","ror":"https://ror.org/00bas1c41","country_code":"PL","type":"education","lineage":["https://openalex.org/I686019"]}],"countries":["PL"],"is_corresponding":true,"raw_author_name":"Daniel Krause","raw_affiliation_strings":["AGH University of Science and Technology, Krak\u00f3w, Poland"],"affiliations":[{"raw_affiliation_string":"AGH University of Science and Technology, Krak\u00f3w, Poland","institution_ids":["https://openalex.org/I686019"]}]},{"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/A5035943967","display_name":"Konrad Kowalczyk","orcid":"https://orcid.org/0000-0002-7834-6920"},"institutions":[{"id":"https://openalex.org/I686019","display_name":"AGH University of Krakow","ror":"https://ror.org/00bas1c41","country_code":"PL","type":"education","lineage":["https://openalex.org/I686019"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Konrad Kowalczyk","raw_affiliation_strings":["AGH University of Science and Technology, Krak\u00f3w, Poland"],"affiliations":[{"raw_affiliation_string":"AGH University of Science and Technology, Krak\u00f3w, Poland","institution_ids":["https://openalex.org/I686019"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5025199613"],"corresponding_institution_ids":["https://openalex.org/I686019"],"apc_list":null,"apc_paid":null,"fwci":1.5241,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.83841424,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"31","last_page":"35"},"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":0.9998999834060669,"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":0.9958999752998352,"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":0.7474293112754822},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.6361246705055237},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5968604683876038},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5647104382514954},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5568903088569641},{"id":"https://openalex.org/keywords/covariance-matrix","display_name":"Covariance matrix","score":0.5180850028991699},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5178854465484619},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5157852172851562},{"id":"https://openalex.org/keywords/acoustic-source-localization","display_name":"Acoustic source localization","score":0.5070521831512451},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4827996492385864},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.475448340177536},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4503844082355499},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44239136576652527},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4314141273498535},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.423176109790802},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.3271426558494568},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1921164095401764},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1452307403087616},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11917755007743835},{"id":"https://openalex.org/keywords/sound-pressure","display_name":"Sound pressure","score":0.06845235824584961}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7474293112754822},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.6361246705055237},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5968604683876038},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5647104382514954},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5568903088569641},{"id":"https://openalex.org/C185142706","wikidata":"https://www.wikidata.org/wiki/Q1134404","display_name":"Covariance matrix","level":2,"score":0.5180850028991699},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5178854465484619},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5157852172851562},{"id":"https://openalex.org/C93240960","wikidata":"https://www.wikidata.org/wiki/Q217270","display_name":"Acoustic source localization","level":3,"score":0.5070521831512451},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4827996492385864},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.475448340177536},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4503844082355499},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44239136576652527},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4314141273498535},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.423176109790802},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.3271426558494568},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1921164095401764},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1452307403087616},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11917755007743835},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.06845235824584961},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/eusipco47968.2020.9287374","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco47968.2020.9287374","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1422086691","https://openalex.org/W1650531274","https://openalex.org/W2046317813","https://openalex.org/W2089368853","https://openalex.org/W2089390156","https://openalex.org/W2092126505","https://openalex.org/W2114863372","https://openalex.org/W2135817141","https://openalex.org/W2137561966","https://openalex.org/W2148154194","https://openalex.org/W2261950180","https://openalex.org/W2384495648","https://openalex.org/W2408239454","https://openalex.org/W2604293017","https://openalex.org/W2622742434","https://openalex.org/W2763971240","https://openalex.org/W2772956764","https://openalex.org/W2810934215","https://openalex.org/W2892163332","https://openalex.org/W2963099423","https://openalex.org/W2963128891","https://openalex.org/W2964342924","https://openalex.org/W2982382207","https://openalex.org/W6628353819","https://openalex.org/W6636898527","https://openalex.org/W6672963529","https://openalex.org/W6736350746","https://openalex.org/W6739564277","https://openalex.org/W6745117180"],"related_works":["https://openalex.org/W1879255185","https://openalex.org/W2769861442","https://openalex.org/W2120442551","https://openalex.org/W1980506188","https://openalex.org/W4240587264","https://openalex.org/W2011788874","https://openalex.org/W2900122540","https://openalex.org/W2041060376","https://openalex.org/W2098651198","https://openalex.org/W2126980866"],"abstract_inverted_index":{"In":[0],"this":[1,131],"paper,":[2],"we":[3,121],"present":[4],"a":[5,9,28,33,42,50,90,95,103],"comparative":[6],"study":[7],"of":[8,11,20,45,61,81,106,137,146,156],"number":[10],"features":[12,110,124,158],"and":[13,25,65,71,115,118,144,161],"time-frequency":[14],"signal":[15],"representations":[16],"for":[17,41,84,130,153],"the":[18,46,59,75,138,150],"task":[19,60,132],"joint":[21,79],"sound":[22,62,66,87],"event":[23,63],"detection":[24,64],"localization":[26,68],"using":[27,49,89],"state-of-the-art":[29,108],"model":[30,92],"based":[31,93],"on":[32,94],"convolutional":[34],"recurrent":[35],"neural":[36,97],"network.":[37],"Experiments":[38],"are":[39,69,159],"performed":[40],"dataset":[43],"consisting":[44],"recordings":[47],"made":[48],"tetrahedral":[51],"microphone":[52,139],"array.":[53],"Several":[54],"feature":[55],"inputs":[56],"specific":[57],"to":[58,77],"source":[67],"combined":[70],"subsequently":[72],"tested,":[73],"with":[74],"aim":[76],"achieve":[78],"performance":[80],"both":[82],"tasks":[83],"multiple":[85],"overlapping":[86],"events":[88],"single":[91],"deep":[96],"network":[98],"architecture.":[99],"Apart":[100],"from":[101],"providing":[102],"comprehensive":[104],"comparison":[105],"various":[107],"acoustic":[109],"such":[111,134],"as":[112,135],"generalized":[113],"cross-correlation,":[114],"inter-channel":[116],"level":[117],"phase":[119,147],"differences,":[120],"propose":[122],"new":[123],"that":[125],"have":[126],"not":[127],"been":[128],"used":[129],"before":[133],"eigenvectors":[136],"covariance":[140],"matrix":[141],"or":[142],"sines":[143],"cosines":[145],"differences":[148],"between":[149],"channels.":[151],"Results":[152],"all":[154],"combinations":[155],"input":[157],"analyzed":[160],"discussed,":[162],"followed":[163],"by":[164],"conclusions.":[165]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3}],"updated_date":"2026-03-25T14:56:36.534964","created_date":"2025-10-10T00:00:00"}