{"id":"https://openalex.org/W4391128510","doi":"https://doi.org/10.1109/taslp.2024.3356987","title":"Speech-Aware Binaural DOA Estimation Utilizing Periodicity and Spatial Features in Convolutional Neural Networks","display_name":"Speech-Aware Binaural DOA Estimation Utilizing Periodicity and Spatial Features in Convolutional Neural Networks","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4391128510","doi":"https://doi.org/10.1109/taslp.2024.3356987"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3356987","doi":"https://doi.org/10.1109/taslp.2024.3356987","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3356987","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["ccf-b","cwts-core","dongbi-a","norway-2","poland-140","russia-white-list-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"volume":null,"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/A5074678647","display_name":"Reza Varzandeh","orcid":"https://orcid.org/0009-0009-0076-2148","observed_orcids":["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":["Department of Medical Physics and Acoustics and the Cluster of Excellence Hearing4all, University of Oldenburg, Oldenburg, 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, 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","observed_orcids":["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, Germany"],"raw_orcid":"https://orcid.org/0000-0002-3392-2381","affiliations":[{"raw_affiliation_string":"Department of Medical Physics and Acoustics and the Cluster of Excellence Hearing4all, University of Oldenburg, 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","observed_orcids":["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, Germany"],"raw_orcid":"https://orcid.org/0000-0001-7056-1880","affiliations":[{"raw_affiliation_string":"Department of Medical Physics and Acoustics and the Cluster of Excellence Hearing4all, University of Oldenburg, 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":{"value":2495,"currency":"USD","value_usd":2495},"apc_paid":null,"fwci":1.8006,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.84755524,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"32","issue":null,"first_page":"1198","last_page":"1213"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9965999722480774,"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":0.9965999722480774,"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/T10931","display_name":"Direction-of-Arrival Estimation Techniques","score":0.0020000000949949026,"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":0.0006000000284984708,"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/binaural-hearing-aids","display_name":"binaural hearing aids","score":0.7770000100135803},{"id":"https://openalex.org/keywords/spatial-characteristics","display_name":"spatial characteristics","score":0.6579999923706055},{"id":"https://openalex.org/keywords/cross-power-spectrum","display_name":"cross-power spectrum","score":0.8149999976158142},{"id":"https://openalex.org/keywords/gcc-phat","display_name":"GCC-PHAT","score":0.8830000162124634},{"id":"https://openalex.org/keywords/speech-non-speech-discrimination","display_name":"speech/non-speech discrimination","score":0.5460000038146973},{"id":"https://openalex.org/keywords/reverberant-environments","display_name":"reverberant environments","score":0.8550000190734863},{"id":"https://openalex.org/keywords/noise-robustness","display_name":"noise robustness","score":0.609000027179718},{"id":"https://openalex.org/keywords/convolutional-neural-networks","display_name":"convolutional neural networks","score":0.7459999918937683}],"concepts":[{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7514725923538208},{"id":"https://openalex.org/C201247586","wikidata":"https://www.wikidata.org/wiki/Q5612967","display_name":"Binaural recording","level":2,"score":0.7435460686683655},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6636885404586792},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6425358653068542},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5109519362449646},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.5027298927307129},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.437167763710022},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.43629881739616394},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08091413974761963},{"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:10.1109/taslp.2024.3356987","doi":"https://doi.org/10.1109/taslp.2024.3356987","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3356987","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["ccf-b","cwts-core","dongbi-a","norway-2","poland-140","russia-white-list-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"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"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W204577949","https://openalex.org/W1522301498","https://openalex.org/W1603075283","https://openalex.org/W1988272246","https://openalex.org/W2009649672","https://openalex.org/W2013312573","https://openalex.org/W2046317813","https://openalex.org/W2052666245","https://openalex.org/W2095425552","https://openalex.org/W2111854888","https://openalex.org/W2113067468","https://openalex.org/W2174451236","https://openalex.org/W2199505332","https://openalex.org/W2294317068","https://openalex.org/W2403149086","https://openalex.org/W2408049710","https://openalex.org/W2592109325","https://openalex.org/W2623647742","https://openalex.org/W2751646960","https://openalex.org/W2765962757","https://openalex.org/W2767191275","https://openalex.org/W2772736377","https://openalex.org/W2795783309","https://openalex.org/W2797059367","https://openalex.org/W2807432252","https://openalex.org/W2885219692","https://openalex.org/W2888842465","https://openalex.org/W2897977894","https://openalex.org/W2903510073","https://openalex.org/W2921741089","https://openalex.org/W2932055495","https://openalex.org/W2954930777","https://openalex.org/W2970971581","https://openalex.org/W2994067526","https://openalex.org/W3015894695","https://openalex.org/W3018444344","https://openalex.org/W3021261768","https://openalex.org/W3029436999","https://openalex.org/W3037932933","https://openalex.org/W3083274258","https://openalex.org/W3129910207","https://openalex.org/W3138975519","https://openalex.org/W3157836681","https://openalex.org/W3197097128","https://openalex.org/W4210381071","https://openalex.org/W4233392025","https://openalex.org/W4285550691","https://openalex.org/W4320013820","https://openalex.org/W6789826613"],"related_works":["https://openalex.org/W4388117844","https://openalex.org/W4407066193","https://openalex.org/W3015894695","https://openalex.org/W4390972457","https://openalex.org/W7155073888","https://openalex.org/W3119066640","https://openalex.org/W2611943505","https://openalex.org/W4289830149","https://openalex.org/W4312278731","https://openalex.org/W4213377681"],"abstract_inverted_index":{"In":[0,26,52],"recent":[1],"years,":[2],"several":[3],"supervised":[4],"learning-based":[5],"approaches":[6],"have":[7],"been":[8],"proposed":[9],"for":[10,62,145,243,267],"estimating":[11],"the":[12,27,39,105,107,111,116,139,151,179,185,202,210,253],"direction":[13],"of":[14,17,29,78,93,141,153,178,193,201,222,261,273],"arrival":[15],"(DOA)":[16],"a":[18,34,57,70,76,94,172,189,223,228,233],"single":[19],"talker":[20],"in":[21,115,218,236,256,271],"noisy":[22],"and":[23,101,125,188,209,246,275],"reverberant":[24,237],"environments.":[25],"absence":[28],"auxiliary":[30],"information,":[31],"such":[32],"as":[33,90,184],"voice":[35],"activity":[36],"detector":[37],"(VAD),":[38],"estimated":[40],"DOA":[41,59,133,147,269],"may":[42],"be":[43],"erroneous":[44],"due":[45],"to":[46,130,165,170],"speech":[47,100,121,135],"pauses":[48],"or":[49,160],"noise":[50],"dominance.":[51],"this":[53,219],"paper,":[54],"we":[55,149],"consider":[56],"speech-aware":[58,146,154],"estimation":[60,270],"system":[61,74],"binaural":[63,268],"hearing":[64],"aids,":[65],"which":[66],"does":[67],"not":[68],"require":[69],"separate":[71],"VAD.":[72,234],"This":[73],"utilizes":[75],"combination":[77,176,199],"spatial":[79,128,186,229,262],"features":[80,92,129,144],"with":[81,205,232,239,258],"an":[82,265],"auditory-inspired":[83],"periodicity":[84,87],"feature":[85,162,175,187,198,255,263],"called":[86],"degree":[88],"(PD)":[89],"input":[91],"convolutional":[95],"neural":[96],"network":[97],"(CNN).":[98],"Using":[99],"non-speech":[102,123],"signals":[103],"during":[104],"training,":[106],"CNN":[108,224],"can":[109],"capture":[110],"harmonic":[112],"structure":[113],"encoded":[114],"PD":[117,143,194,212,254],"features,":[118],"thereby":[119],"distinguishing":[120],"from":[122],"portions":[124],"simultaneously":[126],"mapping":[127],"sound":[131],"source":[132],"upon":[134],"detection.":[136],"To":[137],"investigate":[138],"benefit":[140],"using":[142],"estimation,":[148],"evaluated":[150],"performance":[152],"systems":[155,216],"that":[156,225,251],"utilized":[157],"either":[158],"broadband":[159,197,211],"narrowband":[161,174,180],"combinations":[163],"compared":[164],"baseline":[166,215],"systems.":[167],"We":[168],"propose":[169],"use":[171],"novel":[173],"consisting":[177],"cross-power":[181],"spectrum":[182],"(CPS)":[183],"new":[190],"subband-averaged":[191],"representation":[192],"features.":[195,213],"The":[196,214],"consisted":[200,221],"generalized":[203],"cross-correlation":[204],"phase":[206],"transform":[207],"(GCC-PHAT)":[208],"considered":[217],"work":[220],"exploits":[226],"only":[227],"feature,":[230],"cascaded":[231],"Evaluations":[235],"environments":[238],"different":[240],"background":[241],"noises":[242],"both":[244],"static":[245],"dynamic":[247],"single-talker":[248],"scenarios":[249],"demonstrate":[250],"incorporating":[252],"conjunction":[257],"any":[259],"type":[260],"provides":[264],"advantage":[266],"terms":[272],"accuracy":[274],"angular":[276],"error.":[277]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":1}],"updated_date":"2026-10-26T11:51:55.731654","created_date":"2024-01-24T00:00:00"}