{"id":"https://openalex.org/W4407066193","doi":"https://doi.org/10.1186/s13636-025-00392-8","title":"Improving multi-talker binaural DOA estimation by combining periodicity and spatial features in convolutional neural networks","display_name":"Improving multi-talker binaural DOA estimation by combining periodicity and spatial features in convolutional neural networks","publication_year":2025,"publication_date":"2025-02-01","ids":{"openalex":"https://openalex.org/W4407066193","doi":"https://doi.org/10.1186/s13636-025-00392-8"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-025-00392-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-025-00392-8","pdf_url":"https://link.springer.com/content/pdf/10.1186/s13636-025-00392-8.pdf","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://link.springer.com/content/pdf/10.1186/s13636-025-00392-8.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074678647","display_name":"Reza Varzandeh","orcid":"https://orcid.org/0009-0009-0076-2148"},"institutions":[{"id":"https://openalex.org/I129877168","display_name":"Carl von Ossietzky Universit\u00e4t Oldenburg","ror":"https://ror.org/033n9gh91","country_code":"DE","type":"education","lineage":["https://openalex.org/I129877168"]},{"id":"https://openalex.org/I4210144375","display_name":"Hearing4all","ror":"https://ror.org/0393vzh87","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210144375"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Reza Varzandeh","raw_affiliation_strings":["Department of Medical Physics and Acoustics and the Cluster of Excellence Hearing4all, University of Oldenburg, Oldenburg, 26111, Germany"],"raw_orcid":"https://orcid.org/0009-0009-0076-2148","affiliations":[{"raw_affiliation_string":"Department of Medical Physics and Acoustics and the Cluster of Excellence Hearing4all, University of Oldenburg, Oldenburg, 26111, Germany","institution_ids":["https://openalex.org/I129877168","https://openalex.org/I4210144375"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062526199","display_name":"Simon Doclo","orcid":"https://orcid.org/0000-0002-3392-2381"},"institutions":[{"id":"https://openalex.org/I129877168","display_name":"Carl von Ossietzky Universit\u00e4t Oldenburg","ror":"https://ror.org/033n9gh91","country_code":"DE","type":"education","lineage":["https://openalex.org/I129877168"]},{"id":"https://openalex.org/I4210144375","display_name":"Hearing4all","ror":"https://ror.org/0393vzh87","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210144375"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Simon Doclo","raw_affiliation_strings":["Department of Medical Physics and Acoustics and the Cluster of Excellence Hearing4all, University of Oldenburg, Oldenburg, 26111, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Medical Physics and Acoustics and the Cluster of Excellence Hearing4all, University of Oldenburg, Oldenburg, 26111, Germany","institution_ids":["https://openalex.org/I129877168","https://openalex.org/I4210144375"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002002386","display_name":"Volker Hohmann","orcid":"https://orcid.org/0000-0001-7056-1880"},"institutions":[{"id":"https://openalex.org/I129877168","display_name":"Carl von Ossietzky Universit\u00e4t Oldenburg","ror":"https://ror.org/033n9gh91","country_code":"DE","type":"education","lineage":["https://openalex.org/I129877168"]},{"id":"https://openalex.org/I4210144375","display_name":"Hearing4all","ror":"https://ror.org/0393vzh87","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210144375"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Volker Hohmann","raw_affiliation_strings":["Department of Medical Physics and Acoustics and the Cluster of Excellence Hearing4all, University of Oldenburg, Oldenburg, 26111, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Medical Physics and Acoustics and the Cluster of Excellence Hearing4all, University of Oldenburg, Oldenburg, 26111, Germany","institution_ids":["https://openalex.org/I129877168","https://openalex.org/I4210144375"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5074678647"],"corresponding_institution_ids":["https://openalex.org/I129877168","https://openalex.org/I4210144375"],"apc_list":{"value":1635,"currency":"USD","value_usd":1635},"apc_paid":{"value":1635,"currency":"USD","value_usd":1635},"fwci":2.568,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.88015123,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"2025","issue":"1","first_page":null,"last_page":null},"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/T11698","display_name":"Underwater Acoustics Research","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1910","display_name":"Oceanography"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11447","display_name":"Blind Source Separation Techniques","score":0.9969000220298767,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.9211888909339905},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7691612243652344},{"id":"https://openalex.org/keywords/binaural-recording","display_name":"Binaural recording","score":0.6827614903450012},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46276727318763733},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4450395703315735},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4235125184059143},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3957536518573761}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9211888909339905},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7691612243652344},{"id":"https://openalex.org/C201247586","wikidata":"https://www.wikidata.org/wiki/Q5612967","display_name":"Binaural recording","level":2,"score":0.6827614903450012},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46276727318763733},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4450395703315735},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4235125184059143},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3957536518573761}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1186/s13636-025-00392-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-025-00392-8","pdf_url":"https://link.springer.com/content/pdf/10.1186/s13636-025-00392-8.pdf","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:a9f41b4ae23c4f23bdbc592a377c4602","is_oa":true,"landing_page_url":"https://doaj.org/article/a9f41b4ae23c4f23bdbc592a377c4602","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing, Vol 2025, Iss 1, Pp 1-18 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13636-025-00392-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-025-00392-8","pdf_url":"https://link.springer.com/content/pdf/10.1186/s13636-025-00392-8.pdf","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3825870578","display_name":"SFB 1330: H\u00f6rakustik: Perzeptive Prinzipien, Algorithmen und Anwendungen","funder_award_id":"352015383","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G7238242471","display_name":null,"funder_award_id":"SFB 1330 B2","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G7821612097","display_name":null,"funder_award_id":"SFB 1330","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320319088","display_name":"Carl von Ossietzky Universit\u00e4t Oldenburg","ror":"https://ror.org/033n9gh91"},{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4407066193.pdf"},"referenced_works_count":53,"referenced_works":["https://openalex.org/W222641635","https://openalex.org/W1603075283","https://openalex.org/W1965159237","https://openalex.org/W1987906574","https://openalex.org/W2009649672","https://openalex.org/W2046317813","https://openalex.org/W2097117768","https://openalex.org/W2106272332","https://openalex.org/W2113067468","https://openalex.org/W2153248083","https://openalex.org/W2155323221","https://openalex.org/W2166682639","https://openalex.org/W2174451236","https://openalex.org/W2199505332","https://openalex.org/W2222512263","https://openalex.org/W2408049710","https://openalex.org/W2568308529","https://openalex.org/W2623647742","https://openalex.org/W2765962757","https://openalex.org/W2772736377","https://openalex.org/W2797059367","https://openalex.org/W2807432252","https://openalex.org/W2885219692","https://openalex.org/W2897977894","https://openalex.org/W2921741089","https://openalex.org/W2947942791","https://openalex.org/W2962979155","https://openalex.org/W2963339453","https://openalex.org/W2964342924","https://openalex.org/W3011890046","https://openalex.org/W3015894695","https://openalex.org/W3018444344","https://openalex.org/W3021261768","https://openalex.org/W3029436999","https://openalex.org/W3102937397","https://openalex.org/W3105684258","https://openalex.org/W3129910207","https://openalex.org/W3132830522","https://openalex.org/W3138975519","https://openalex.org/W3160878746","https://openalex.org/W3197097128","https://openalex.org/W4210381071","https://openalex.org/W4210774825","https://openalex.org/W4213377681","https://openalex.org/W4285550691","https://openalex.org/W4312873392","https://openalex.org/W4366967194","https://openalex.org/W4372260199","https://openalex.org/W4372262494","https://openalex.org/W4388117844","https://openalex.org/W4390096820","https://openalex.org/W4391128510","https://openalex.org/W6602575196"],"related_works":["https://openalex.org/W2766995619","https://openalex.org/W4224270619","https://openalex.org/W2579722767","https://openalex.org/W2168148781","https://openalex.org/W1991848873","https://openalex.org/W2026165661","https://openalex.org/W2099651033","https://openalex.org/W2783525307","https://openalex.org/W2593008828","https://openalex.org/W2051487156"],"abstract_inverted_index":{"Abstract":[0],"Deep":[1],"neural":[2,71],"network-based":[3],"direction":[4],"of":[5,25,33,45,52,58,123,149,178],"arrival":[6],"(DOA)":[7],"estimation":[8,36,81,221,243],"systems":[9,189],"often":[10],"rely":[11],"on":[12],"spatial":[13,64,95],"features":[14,54,65,96,181,196,213],"as":[15,55,66,94,106],"input":[16,67],"to":[17,29,68,119,251],"learn":[18],"a":[19,42,56,69,78,84,113,252],"mapping":[20],"for":[21,37,134,261],"estimating":[22],"the":[23,31,50,120,135,150,176,215,227,232,238],"DOA":[24,35,80,220,242,263],"multiple":[26],"talkers.":[27],"Aiming":[28],"improve":[30],"accuracy":[32,222,244],"multi-talker":[34,79,262],"binaural":[38],"hearing":[39],"aids":[40],"with":[41,63,159,182],"known":[43],"number":[44],"active":[46],"talkers,":[47],"we":[48,76,186],"investigate":[49,130],"usage":[51],"periodicity":[53,100,103],"footprint":[57],"speech":[59],"signals":[60],"in":[61,155,162,214,237],"combination":[62],"convolutional":[70],"network":[72],"(CNN).":[73],"In":[74],"particular,":[75],"propose":[77],"system":[82,152,217,240,254],"employing":[83],"two-stage":[85,110],"CNN":[86,111,136],"architecture":[87],"that":[88,190,207],"utilizes":[89],"cross-power":[90],"spectrum":[91],"(CPS)":[92],"phase":[93,127,184,195,200,212],"and":[97,125,143,201,210],"an":[98],"auditory-inspired":[99],"feature":[101,115,234],"called":[102],"degree":[104],"(PD)":[105],"spectral":[107],"features.":[108,128,204],"The":[109,147],"incorporates":[112],"PD":[114,124,180,209,233],"reduction":[116,141,235],"stage":[117,236],"prior":[118],"joint":[121],"processing":[122],"CPS":[126,183,194,199,211],"We":[129],"different":[131],"design":[132],"choices":[133],"architecture,":[137],"including":[138],"varying":[139,167],"temporal":[140],"strategies":[142],"spectro-temporal":[144],"filtering":[145],"approaches.":[146],"performance":[148],"proposed":[151,216,239],"is":[153],"evaluated":[154],"static":[156],"source":[157],"scenarios":[158],"2\u20133":[160],"talkers":[161],"two":[163,228],"reverberant":[164],"environments":[165],"under":[166],"signal-to-noise":[168],"ratios":[169],"using":[170],"recorded":[171],"background":[172],"noises.":[173],"To":[174],"evaluate":[175],"benefit":[177],"combining":[179,208],"features,":[185],"consider":[187],"baseline":[188,229,253],"utilize":[191],"either":[192],"only":[193],"or":[197],"combine":[198],"magnitude":[202],"spectrogram":[203],"Results":[205],"show":[206],"consistently":[218],"improves":[219,241],"across":[223],"all":[224],"conditions,":[225],"outperforming":[226],"systems.":[230],"Additionally,":[231],"while":[245],"significantly":[246],"reducing":[247],"computational":[248],"complexity":[249],"compared":[250],"without":[255],"this":[256],"stage,":[257],"demonstrating":[258],"its":[259],"effectiveness":[260],"estimation.":[264]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}