{"id":"https://openalex.org/W4391235393","doi":"https://doi.org/10.1109/taslp.2024.3357037","title":"Neural-Network-Based Direction-of-Arrival Estimation for Reverberant Speech - The Importance of Energetic, Temporal, and Spatial Information","display_name":"Neural-Network-Based Direction-of-Arrival Estimation for Reverberant Speech - The Importance of Energetic, Temporal, and Spatial Information","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4391235393","doi":"https://doi.org/10.1109/taslp.2024.3357037"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3357037","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3357037","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10414159.pdf","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,"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"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10414159.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039925714","display_name":"Orel Ben Zaken","orcid":"https://orcid.org/0009-0007-6596-6489"},"institutions":[{"id":"https://openalex.org/I124227911","display_name":"Ben-Gurion University of the Negev","ror":"https://ror.org/05tkyf982","country_code":"IL","type":"education","lineage":["https://openalex.org/I124227911"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Orel Ben Zaken","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Ben-Gurion University of the Negev, Beer-Sheva, Israel"],"raw_orcid":"https://orcid.org/0009-0007-6596-6489","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Ben-Gurion University of the Negev, Beer-Sheva, Israel","institution_ids":["https://openalex.org/I124227911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066528816","display_name":"Anurag Kumar","orcid":"https://orcid.org/0000-0002-9621-9888"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anurag Kumar","raw_affiliation_strings":["Facebook Reality Labs, Facebook Inc., Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook Reality Labs, Facebook Inc., Redmond, WA, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026575041","display_name":"Vladimir Tourbabin","orcid":"https://orcid.org/0000-0003-2536-5666"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vladimir Tourbabin","raw_affiliation_strings":["Facebook Seattle, Seattle, WA, USA"],"raw_orcid":"https://orcid.org/0000-0003-2536-5666","affiliations":[{"raw_affiliation_string":"Facebook Seattle, Seattle, WA, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019518606","display_name":"Boaz Rafaely","orcid":"https://orcid.org/0000-0002-6819-9250"},"institutions":[{"id":"https://openalex.org/I124227911","display_name":"Ben-Gurion University of the Negev","ror":"https://ror.org/05tkyf982","country_code":"IL","type":"education","lineage":["https://openalex.org/I124227911"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Boaz Rafaely","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Ben-Gurion University of the Negev, Beer-Sheva, Israel"],"raw_orcid":"https://orcid.org/0000-0002-6819-9250","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Ben-Gurion University of the Negev, Beer-Sheva, Israel","institution_ids":["https://openalex.org/I124227911"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8343,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.84599078,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"32","issue":null,"first_page":"1298","last_page":"1309"},"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":0.9973000288009644,"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":0.9970999956130981,"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":0.7858515381813049},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.687751054763794},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.6468635201454163},{"id":"https://openalex.org/keywords/direction-of-arrival","display_name":"Direction of arrival","score":0.5889519453048706},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5847832560539246},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4920351207256317},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45597586035728455},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3765886425971985},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3538752794265747},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.11663711071014404},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08556073904037476}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7858515381813049},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.687751054763794},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.6468635201454163},{"id":"https://openalex.org/C172051844","wikidata":"https://www.wikidata.org/wiki/Q5280438","display_name":"Direction of arrival","level":3,"score":0.5889519453048706},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5847832560539246},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4920351207256317},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45597586035728455},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3765886425971985},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3538752794265747},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.11663711071014404},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08556073904037476},{"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2024.3357037","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3357037","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10414159.pdf","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,"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":{"id":"doi:10.1109/taslp.2024.3357037","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3357037","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10414159.pdf","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,"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4391235393.pdf","grobid_xml":"https://content.openalex.org/works/W4391235393.grobid-xml"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W1503398984","https://openalex.org/W1522301498","https://openalex.org/W1585864165","https://openalex.org/W1603075283","https://openalex.org/W1964998538","https://openalex.org/W1966081805","https://openalex.org/W2015245929","https://openalex.org/W2037551711","https://openalex.org/W2037814094","https://openalex.org/W2046317813","https://openalex.org/W2050551142","https://openalex.org/W2056212252","https://openalex.org/W2060108923","https://openalex.org/W2113638573","https://openalex.org/W2114863372","https://openalex.org/W2117678320","https://openalex.org/W2231821870","https://openalex.org/W2283105982","https://openalex.org/W2319660501","https://openalex.org/W2403149086","https://openalex.org/W2552290276","https://openalex.org/W2557731587","https://openalex.org/W2605834669","https://openalex.org/W2663904211","https://openalex.org/W2747438053","https://openalex.org/W2885219692","https://openalex.org/W2888793942","https://openalex.org/W2903697385","https://openalex.org/W2903950532","https://openalex.org/W2962866211","https://openalex.org/W2964342924","https://openalex.org/W2989691494","https://openalex.org/W3021261768","https://openalex.org/W3042293613","https://openalex.org/W3097253667","https://openalex.org/W3100336094","https://openalex.org/W3100987222","https://openalex.org/W3102937397","https://openalex.org/W3127686677","https://openalex.org/W3196420731","https://openalex.org/W3197097128","https://openalex.org/W4239510810","https://openalex.org/W4249052411","https://openalex.org/W4250857377","https://openalex.org/W4312278731","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6659849957","https://openalex.org/W6789826613","https://openalex.org/W7046848240"],"related_works":["https://openalex.org/W1656519308","https://openalex.org/W2042717753","https://openalex.org/W2022849831","https://openalex.org/W2037265366","https://openalex.org/W2026603686","https://openalex.org/W2331622705","https://openalex.org/W2391832549","https://openalex.org/W4401069787","https://openalex.org/W1499578372","https://openalex.org/W2368849850"],"abstract_inverted_index":{"Direction-of-arrival":[0],"(DOA)":[1],"estimation":[2],"is":[3,98,126],"a":[4,87,109,121,141,190,195],"fundamental":[5],"task":[6],"in":[7,14,194,223],"audio":[8],"signal":[9],"processing":[10],"that":[11,114,207],"becomes":[12],"difficult":[13],"real-world":[15],"environments":[16],"due":[17],"to":[18,56,75,128,144,171],"the":[19,77,84,95,116,130,133,150,155,161,172,178],"presence":[20],"of":[21,94,132,174,189],"reverberation.":[22],"To":[23],"address":[24],"this":[25],"difficulty,":[26],"Direct-Path":[27],"Dominance":[28],"(DPD)":[29],"tests":[30],"have":[31,53,72,80],"been":[32,54,73,221],"proposed":[33,182],"as":[34,83],"an":[35],"effective":[36],"approach":[37,113,143],"for":[38,86],"detecting":[39],"time-frequency":[40],"(TF)":[41],"bins":[42],"dominated":[43,176],"by":[44,177],"direct":[45,151,179,216],"sound,":[46,152,217],"which":[47,218],"contain":[48],"accurate":[49],"DOA":[50],"information.":[51],"These":[52],"found":[55],"be":[57],"particularly":[58],"efficient":[59],"when":[60],"working":[61],"with":[62,120],"spherical":[63],"arrays.":[64],"While":[65],"methods":[66,106,183],"based":[67,107],"on":[68,108,186,199],"neural":[69],"networks":[70],"(NNs)":[71],"developed":[74],"estimate":[76],"DOA,":[78],"they":[79],"limitations":[81],"such":[82],"need":[85],"large":[88],"training":[89],"database,":[90],"and":[91,167,197,201,209,226],"often":[92],"understanding":[93],"system's":[96],"operation":[97],"lacking.":[99],"This":[100],"work":[101],"proposes":[102],"two":[103],"novel":[104],"DPD-test":[105,118,135],"model-based":[110],"deep":[111],"learning":[112],"combines":[115],"original":[117,134,156],"model":[119],"data-driven":[122,142],"system.":[123],"Thus,":[124],"it":[125],"possible":[127],"preserve":[129],"robustness":[131],"across":[136],"acoustic":[137],"environments,":[138],"while":[139],"using":[140],"better":[145],"extract":[146],"useful":[147],"information":[148,169,211,214],"about":[149,215],"thereby":[153],"enhancing":[154],"method's":[157],"performance.":[158,230],"In":[159],"particular,":[160],"paper":[162],"investigates":[163],"how":[164],"energetic,":[165],"temporal":[166,210],"spatial":[168],"contribute":[170],"identification":[173],"TF-bins":[175],"signal.":[180],"The":[181,204],"are":[184],"trained":[185],"simulated":[187,200],"data":[188],"single":[191],"sound":[192],"source":[193],"room,":[196],"evaluated":[198],"real":[202],"data.":[203],"results":[205],"show":[206],"energetic":[208],"provide":[212],"new":[213],"has":[219],"not":[220],"considered":[222],"previous":[224],"works":[225],"can":[227],"improve":[228],"its":[229]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}