{"id":"https://openalex.org/W4388117844","doi":"https://doi.org/10.23919/eusipco58844.2023.10290054","title":"A Two-Stage CNN with Feature Reduction for Speech-Aware Binaural DOA Estimation","display_name":"A Two-Stage CNN with Feature Reduction for Speech-Aware Binaural DOA Estimation","publication_year":2023,"publication_date":"2023-09-04","ids":{"openalex":"https://openalex.org/W4388117844","doi":"https://doi.org/10.23919/eusipco58844.2023.10290054"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco58844.2023.10290054","is_oa":false,"landing_page_url":"http://dx.doi.org/10.23919/eusipco58844.2023.10290054","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 31st 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/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":false,"raw_author_name":"Reza Varzandeh","raw_affiliation_strings":["University of Oldenburg,Department of Medical Physics and Acoustics and Cluster of Excellence Hearing4all,Germany","Department of Medical Physics and Acoustics and Cluster of Excellence Hearing4all, University of Oldenburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oldenburg,Department of Medical Physics and Acoustics and Cluster of Excellence Hearing4all,Germany","institution_ids":["https://openalex.org/I129877168","https://openalex.org/I4210144375"]},{"raw_affiliation_string":"Department of Medical Physics and Acoustics and Cluster of Excellence Hearing4all, University of Oldenburg, 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":["University of Oldenburg,Department of Medical Physics and Acoustics and Cluster of Excellence Hearing4all,Germany","Department of Medical Physics and Acoustics and Cluster of Excellence Hearing4all, University of Oldenburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oldenburg,Department of Medical Physics and Acoustics and Cluster of Excellence Hearing4all,Germany","institution_ids":["https://openalex.org/I129877168","https://openalex.org/I4210144375"]},{"raw_affiliation_string":"Department of Medical Physics and Acoustics and Cluster of Excellence Hearing4all, University of Oldenburg, 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":["University of Oldenburg,Department of Medical Physics and Acoustics and Cluster of Excellence Hearing4all,Germany","Department of Medical Physics and Acoustics and Cluster of Excellence Hearing4all, University of Oldenburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oldenburg,Department of Medical Physics and Acoustics and Cluster of Excellence Hearing4all,Germany","institution_ids":["https://openalex.org/I129877168","https://openalex.org/I4210144375"]},{"raw_affiliation_string":"Department of Medical Physics and Acoustics and Cluster of Excellence Hearing4all, University of Oldenburg, Germany","institution_ids":["https://openalex.org/I129877168","https://openalex.org/I4210144375"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"241","last_page":"245"},"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":0.9975000023841858,"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":0.996999979019165,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/narrowband","display_name":"Narrowband","score":0.7794002294540405},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7706030607223511},{"id":"https://openalex.org/keywords/binaural-recording","display_name":"Binaural recording","score":0.7126772403717041},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6871106624603271},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6306357979774475},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.5502200722694397},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5195779800415039},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5107550621032715},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45367926359176636},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.4462776482105255},{"id":"https://openalex.org/keywords/direction-of-arrival","display_name":"Direction of arrival","score":0.42194652557373047},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11799713969230652}],"concepts":[{"id":"https://openalex.org/C2776096036","wikidata":"https://www.wikidata.org/wiki/Q1140483","display_name":"Narrowband","level":2,"score":0.7794002294540405},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7706030607223511},{"id":"https://openalex.org/C201247586","wikidata":"https://www.wikidata.org/wiki/Q5612967","display_name":"Binaural recording","level":2,"score":0.7126772403717041},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6871106624603271},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6306357979774475},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.5502200722694397},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5195779800415039},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5107550621032715},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45367926359176636},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.4462776482105255},{"id":"https://openalex.org/C172051844","wikidata":"https://www.wikidata.org/wiki/Q5280438","display_name":"Direction of arrival","level":3,"score":0.42194652557373047},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11799713969230652},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/eusipco58844.2023.10290054","is_oa":false,"landing_page_url":"http://dx.doi.org/10.23919/eusipco58844.2023.10290054","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 31st European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6299999952316284,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G7709321326","display_name":null,"funder_award_id":"352015383- SFB 1330B2","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W126779258","https://openalex.org/W1522301498","https://openalex.org/W1987906574","https://openalex.org/W1988272246","https://openalex.org/W2009649672","https://openalex.org/W2046317813","https://openalex.org/W2052666245","https://openalex.org/W2097117768","https://openalex.org/W2174451236","https://openalex.org/W2199505332","https://openalex.org/W2294317068","https://openalex.org/W2408049710","https://openalex.org/W2765962757","https://openalex.org/W2772736377","https://openalex.org/W2885219692","https://openalex.org/W2954930777","https://openalex.org/W2963339453","https://openalex.org/W3003432884","https://openalex.org/W3013253926","https://openalex.org/W3015894695","https://openalex.org/W3021261768","https://openalex.org/W3102937397","https://openalex.org/W3105684258","https://openalex.org/W3127686677","https://openalex.org/W3129910207","https://openalex.org/W3138975519","https://openalex.org/W3197097128","https://openalex.org/W4210381071","https://openalex.org/W4295312788","https://openalex.org/W4310557412","https://openalex.org/W6605165268","https://openalex.org/W6696760643","https://openalex.org/W6766978945","https://openalex.org/W6775354647","https://openalex.org/W6780226713","https://openalex.org/W6789826613"],"related_works":["https://openalex.org/W2766995619","https://openalex.org/W4224270619","https://openalex.org/W2579722767","https://openalex.org/W2168148781","https://openalex.org/W2391187634","https://openalex.org/W1915213138","https://openalex.org/W2157042899","https://openalex.org/W2373910021","https://openalex.org/W1921043431","https://openalex.org/W2128773641"],"abstract_inverted_index":{"In":[0,26,143],"recent":[1],"years,":[2],"several":[3],"supervised":[4],"learning-based":[5],"approaches":[6],"have":[7],"been":[8],"proposed":[9,150],"to":[10,81,90],"estimate":[11],"the":[12,52,59,69,82,92,95,122,125,138,149],"direction":[13],"of":[14,17,54,62,85,94,124,131,140,157],"arrival":[15],"(DOA)":[16],"a":[18,31,44,63,100,153,158,165],"single":[19],"talker":[20],"in":[21,129],"noisy":[22],"and":[23,75,164],"reverberant":[24,115],"environments.":[25],"this":[27],"paper,":[28],"we":[29,88],"consider":[30],"speech-aware":[32],"DOA":[33,132],"estimation":[34,133],"system":[35,151,155],"for":[36,113],"binaural":[37],"hearing":[38],"aids,":[39],"which":[40],"does":[41],"not":[42],"require":[43],"separate":[45],"voice":[46],"activity":[47],"detector":[48],"(VAD).":[49],"We":[50],"propose":[51,89],"combination":[53],"two":[55,114],"narrowband":[56,76,96],"features":[57,61,74,98,163],"as":[58,72],"input":[60],"convolutional":[64],"neural":[65],"network":[66],"(CNN),":[67],"namely":[68],"cross-power":[70],"spectrum":[71],"spatial":[73,162],"auditory-inspired":[77],"periodicity":[78,97],"features.":[79],"Prior":[80],"joint":[83],"processing":[84],"both":[86],"features,":[87],"reduce":[91],"dimensionality":[93],"using":[99,160],"feature":[101,126],"reduction":[102,127],"stage":[103,128],"based":[104],"on":[105],"<tex":[106],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[107],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$1\\times":[108],"1$</tex>":[109],"convolutions.":[110],"Simulation":[111],"results":[112,146],"environments":[116],"with":[117],"different":[118],"background":[119],"noises":[120],"demonstrate":[121],"benefit":[123],"terms":[130],"accuracy":[134],"while":[135],"significantly":[136],"reducing":[137],"number":[139],"trainable":[141],"parameters.":[142],"addition,":[144],"simulation":[145],"show":[147],"that":[148],"outperforms":[152],"baseline":[154],"consisting":[156],"CNN":[159],"only":[161],"pitch-based":[166],"VAD.":[167]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}