{"id":"https://openalex.org/W3117312351","doi":"https://doi.org/10.23919/eusipco47968.2020.9287344","title":"Comparison of Convolution Types in CNN-based Feature Extraction for Sound Source Localization","display_name":"Comparison of Convolution Types in CNN-based Feature Extraction for Sound Source Localization","publication_year":2020,"publication_date":"2020-12-18","ids":{"openalex":"https://openalex.org/W3117312351","doi":"https://doi.org/10.23919/eusipco47968.2020.9287344","mag":"3117312351"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco47968.2020.9287344","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco47968.2020.9287344","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":2.5761,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.90691244,"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":"820","last_page":"824"},"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":0.9988999962806702,"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":0.993399977684021,"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":0.7832421660423279},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.679473876953125},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.6538602709770203},{"id":"https://openalex.org/keywords/short-time-fourier-transform","display_name":"Short-time Fourier transform","score":0.627241313457489},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.6158376336097717},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5365334749221802},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5331088304519653},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4891982078552246},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.48789143562316895},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4707111716270447},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4642845690250397},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.44548335671424866},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.4405743479728699},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.43635815382003784},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.4299495816230774},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.414616197347641},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.358378529548645},{"id":"https://openalex.org/keywords/digital-signal-processing","display_name":"Digital signal processing","score":0.25479352474212646},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.12521350383758545},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1164628267288208},{"id":"https://openalex.org/keywords/fourier-analysis","display_name":"Fourier analysis","score":0.11338064074516296}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7832421660423279},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.679473876953125},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.6538602709770203},{"id":"https://openalex.org/C166386157","wikidata":"https://www.wikidata.org/wiki/Q1477735","display_name":"Short-time Fourier transform","level":4,"score":0.627241313457489},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.6158376336097717},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5365334749221802},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5331088304519653},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4891982078552246},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.48789143562316895},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4707111716270447},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4642845690250397},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.44548335671424866},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.4405743479728699},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.43635815382003784},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.4299495816230774},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.414616197347641},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.358378529548645},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.25479352474212646},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.12521350383758545},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1164628267288208},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.11338064074516296},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/eusipco47968.2020.9287344","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco47968.2020.9287344","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":35,"referenced_works":["https://openalex.org/W1422086691","https://openalex.org/W2033526388","https://openalex.org/W2046317813","https://openalex.org/W2058497647","https://openalex.org/W2092126505","https://openalex.org/W2095425552","https://openalex.org/W2111890897","https://openalex.org/W2113638573","https://openalex.org/W2114863372","https://openalex.org/W2128131274","https://openalex.org/W2137666850","https://openalex.org/W2166682639","https://openalex.org/W2334833135","https://openalex.org/W2384495648","https://openalex.org/W2490695385","https://openalex.org/W2541714600","https://openalex.org/W2586642235","https://openalex.org/W2611943505","https://openalex.org/W2612445135","https://openalex.org/W2618946976","https://openalex.org/W2772956764","https://openalex.org/W2810934215","https://openalex.org/W2948091552","https://openalex.org/W2964342924","https://openalex.org/W3104757150","https://openalex.org/W3127686677","https://openalex.org/W4206633762","https://openalex.org/W4288090873","https://openalex.org/W4297775537","https://openalex.org/W6628353819","https://openalex.org/W6676895149","https://openalex.org/W6729017730","https://openalex.org/W6737664043","https://openalex.org/W6738884980","https://openalex.org/W6789826613"],"related_works":["https://openalex.org/W1879255185","https://openalex.org/W2120442551","https://openalex.org/W2769861442","https://openalex.org/W1980506188","https://openalex.org/W2900122540","https://openalex.org/W4240587264","https://openalex.org/W2043735059","https://openalex.org/W2041060376","https://openalex.org/W3119734852","https://openalex.org/W2011776247"],"abstract_inverted_index":{"This":[0],"paper":[1,130,184],"presents":[2,131,185],"an":[3],"overview":[4],"of":[5,15,26,52,67,87,94,115,135,142],"several":[6,82],"approaches":[7,102],"to":[8,47,75,119],"convolutional":[9,36,78],"feature":[10],"extraction":[11],"in":[12,31,111,139,202],"the":[13,32,45,68,85,95,104,125,132,186,196],"context":[14],"deep":[16],"neural":[17,37,153],"network":[18],"(DNN)":[19],"based":[20,150],"sound":[21,143],"source":[22,144,204],"localization.":[23,145,205],"Different":[24],"ways":[25],"processing":[27,86],"multichannel":[28,91],"audio":[29],"data":[30],"time-frequency":[33],"domain":[34],"using":[35,168,178,189],"networks":[38,154],"(CNNs)":[39],"are":[40,60,103,117,166],"described":[41],"and":[42,64,107,123,174,194,199],"tested":[43],"with":[44,62],"aim":[46],"provide":[48],"a":[49,140,179],"comparative":[50],"study":[51],"their":[53],"performance.":[54],"In":[55,73],"most":[56],"considered":[57],"approaches,":[58],"models":[59],"trained":[61],"phase":[63],"magnitude":[65],"components":[66],"Short-Time":[69],"Fourier":[70],"Transform":[71],"(STFT).":[72],"addition":[74],"state-of-the-art":[76],"2D":[77],"layers,":[79],"we":[80],"investigate":[81],"solutions":[83],"for":[84,157],"3D":[88,105],"matrices":[89],"containing":[90,172],"complex":[92,162],"representation":[93],"microphone":[96,181],"signals.":[97],"The":[98,146,183],"first":[99,133],"two":[100,113,169],"proposed":[101],"convolutions":[106,110,138,159],"depthwise":[108,136],"separable":[109,137],"which":[112,155],"types":[114,193],"filters":[116],"used":[118],"exploit":[120],"information":[121],"within":[122],"between":[124],"channels.":[126],"Note":[127],"that":[128],"this":[129],"application":[134],"task":[141],"third":[147],"approach":[148],"is":[149],"on":[151,161],"complex-valued":[152],"allows":[156],"performing":[158],"directly":[160],"signal":[163],"representations.":[164],"Experiments":[165],"conducted":[167],"synthetic":[170],"datasets":[171],"noise":[173],"speech":[175],"signals":[176],"recorded":[177],"tetrahedral":[180],"array.":[182],"results":[187],"obtained":[188],"all":[190],"investigated":[191],"model":[192],"discusses":[195],"resulting":[197],"accuracy":[198],"computational":[200],"complexity":[201],"DNN-based":[203]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}