{"id":"https://openalex.org/W3095737053","doi":"https://doi.org/10.1109/access.2020.3033533","title":"Spectral Flux-Based Convolutional Neural Network Architecture for Speech Source Localization and its Real-Time Implementation","display_name":"Spectral Flux-Based Convolutional Neural Network Architecture for Speech Source Localization and its Real-Time Implementation","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3095737053","doi":"https://doi.org/10.1109/access.2020.3033533","mag":"3095737053","pmid":"https://pubmed.ncbi.nlm.nih.gov/33981519"},"language":"en","primary_location":{"id":"doi:10.1109/access.2020.3033533","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.3033533","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09239325.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09239325.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007703197","display_name":"Yiya Hao","orcid":"https://orcid.org/0000-0003-1234-4209"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yiya Hao","raw_affiliation_strings":["Department of Electrical and Computer Engineering, The University of Texas at Dallas, Richardson, TX 75080, USA","The University of Texas at Dallas, Richardson, TX, USA"],"raw_orcid":"https://orcid.org/0000-0003-1234-4209","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, The University of Texas at Dallas, Richardson, TX 75080, USA","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"The University of Texas at Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039525680","display_name":"Abdullah K\u00fc\u00e7\u00fck","orcid":"https://orcid.org/0000-0001-9589-688X"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abdullah Kucuk","raw_affiliation_strings":["Department of Electrical and Computer Engineering, The University of Texas at Dallas, Richardson, TX 75080, USA","The University of Texas at Dallas, Richardson, TX, USA"],"raw_orcid":"https://orcid.org/0000-0001-9589-688X","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, The University of Texas at Dallas, Richardson, TX 75080, USA","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"The University of Texas at Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074240675","display_name":"Anshuman Ganguly","orcid":"https://orcid.org/0000-0003-4409-3088"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anshuman Ganguly","raw_affiliation_strings":["Department of Electrical and Computer Engineering, The University of Texas at Dallas, Richardson, TX 75080, USA","The University of Texas at Dallas, Richardson, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, The University of Texas at Dallas, Richardson, TX 75080, USA","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"The University of Texas at Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066837968","display_name":"Issa Panahi","orcid":"https://orcid.org/0000-0002-1852-3104"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Issa M. S. Panahi","raw_affiliation_strings":["Department of Electrical and Computer Engineering, The University of Texas at Dallas, Richardson, TX 75080, USA","The University of Texas at Dallas, Richardson, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, The University of Texas at Dallas, Richardson, TX 75080, USA","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"The University of Texas at Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":1.6726,"has_fulltext":true,"cited_by_count":19,"citation_normalized_percentile":{"value":0.84906399,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"8","issue":null,"first_page":"197047","last_page":"197058"},"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.836822509765625},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6972593069076538},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6378125548362732},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.567466139793396},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.5057413578033447},{"id":"https://openalex.org/keywords/short-time-fourier-transform","display_name":"Short-time Fourier transform","score":0.4654078781604767},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44957128167152405},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.44775670766830444},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.4288427233695984},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3891984820365906},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.33838367462158203},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.28868305683135986},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1053667664527893},{"id":"https://openalex.org/keywords/fourier-analysis","display_name":"Fourier analysis","score":0.10392692685127258},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09122994542121887}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.836822509765625},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6972593069076538},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6378125548362732},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.567466139793396},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.5057413578033447},{"id":"https://openalex.org/C166386157","wikidata":"https://www.wikidata.org/wiki/Q1477735","display_name":"Short-time Fourier transform","level":4,"score":0.4654078781604767},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44957128167152405},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.44775670766830444},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.4288427233695984},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3891984820365906},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.33838367462158203},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.28868305683135986},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1053667664527893},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.10392692685127258},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09122994542121887},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/access.2020.3033533","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.3033533","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09239325.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmid:33981519","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33981519","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE access : practical innovations, open solutions","raw_type":null},{"id":"pmh:oai:doaj.org/article:acb76dcd136a42c18fa97ab8d21bda0e","is_oa":true,"landing_page_url":"https://doaj.org/article/acb76dcd136a42c18fa97ab8d21bda0e","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":"IEEE Access, Vol 8, Pp 197047-197058 (2020)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:8112575","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8112575","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1109/access.2020.3033533","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.3033533","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09239325.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4454965963","display_name":null,"funder_award_id":"1R01DC015430-05","funder_id":"https://openalex.org/F4320337352","funder_display_name":"National Institute on Deafness and Other Communication Disorders"},{"id":"https://openalex.org/G872832014","display_name":null,"funder_award_id":"R01 DC015430","funder_id":"https://openalex.org/F4320337352","funder_display_name":"National Institute on Deafness and Other Communication Disorders"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320333766","display_name":"Department of Electrical and Computer Engineering, University of Texas at Dallas","ror":null},{"id":"https://openalex.org/F4320337352","display_name":"National Institute on Deafness and Other Communication Disorders","ror":"https://ror.org/04mhx6838"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3095737053.pdf","grobid_xml":"https://content.openalex.org/works/W3095737053.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W14578209","https://openalex.org/W217932999","https://openalex.org/W246421128","https://openalex.org/W827360215","https://openalex.org/W1603075283","https://openalex.org/W1665214252","https://openalex.org/W1975675577","https://openalex.org/W1977167953","https://openalex.org/W2048541712","https://openalex.org/W2061074721","https://openalex.org/W2100471625","https://openalex.org/W2102764819","https://openalex.org/W2113638573","https://openalex.org/W2123263496","https://openalex.org/W2341692836","https://openalex.org/W2402144811","https://openalex.org/W2486913545","https://openalex.org/W2536470260","https://openalex.org/W2753024126","https://openalex.org/W2757826220","https://openalex.org/W2766086962","https://openalex.org/W2772736377","https://openalex.org/W2776323726","https://openalex.org/W2802108787","https://openalex.org/W2885219692","https://openalex.org/W2953384591","https://openalex.org/W2994067526","https://openalex.org/W3104947433","https://openalex.org/W3105684258","https://openalex.org/W4249052411","https://openalex.org/W6600580371","https://openalex.org/W6637242042","https://openalex.org/W6644815614","https://openalex.org/W6704261492","https://openalex.org/W6713134421","https://openalex.org/W6743853957"],"related_works":["https://openalex.org/W1656519308","https://openalex.org/W2042717753","https://openalex.org/W2022849831","https://openalex.org/W2037265366","https://openalex.org/W2391832549","https://openalex.org/W2286653370","https://openalex.org/W1499578372","https://openalex.org/W2368849850","https://openalex.org/W2088447702","https://openalex.org/W2402466562"],"abstract_inverted_index":{"In":[0],"this":[1,187],"article,":[2],"we":[3,169],"present":[4],"a":[5,36,150,171],"real-time":[6,41,131,175],"convolutional":[7],"neural":[8],"network":[9],"(CNN)-based":[10],"Speech":[11],"source":[12],"localization":[13],"(SSL)":[14],"algorithm":[15],"that":[16,185],"is":[17],"robust":[18],"to":[19,122],"realistic":[20,103],"background":[21],"acoustic":[22],"conditions":[23],"(noise":[24],"and":[25,30,58,84,106,156,177,210],"reverberation).":[26],"We":[27,43,70,90,129],"have":[28,44,71],"implemented":[29],"tested":[31],"the":[32,46,49,53,67,73,112,138,202],"proposed":[33],"method":[34],"on":[35,86,137],"prototype":[37],"(Raspberry":[38],"Pi)":[39],"for":[40,200,205],"operation.":[42],"used":[45],"combination":[47],"of":[48,52,133,153,174],"imaginary-real":[50],"coefficients":[51],"short-time":[54],"Fourier":[55],"transform":[56],"(STFT)":[57],"Spectral":[59,113],"Flux":[60,114],"(SF)":[61,115],"with":[62,94,116,141,149],"delay-and-sum":[63],"(DAS)":[64],"beamforming":[65,117],"as":[66,118],"input":[68],"feature.":[69],"trained":[72],"CNN":[74,135],"model":[75,136],"using":[76],"noisy":[77,104],"speech":[78,127],"recordings":[79],"collected":[80],"from":[81,190],"different":[82],"rooms":[83],"inference":[85],"an":[87,119],"unseen":[88],"room.":[89],"provide":[91,170],"quantitative":[92],"comparison":[93],"five":[95],"other":[96],"previously":[97,191],"published":[98,192],"SSL":[99],"algorithms":[100,204],"under":[101,161],"several":[102,197],"conditions,":[105],"show":[107],"significant":[108],"improvements":[109],"by":[110],"incorporating":[111],"additional":[120],"feature":[121],"learn":[123],"temporal":[124],"variation":[125],"in":[126],"spectra.":[128],"perform":[130],"inferencing":[132],"our":[134],"prototyped":[139],"platform":[140],"low":[142],"latency":[143],"(21":[144],"milliseconds":[145],"(ms)":[146],"per":[147],"frame":[148,151],"length":[152],"30":[154],"ms)":[155],"high":[157],"accuracy":[158],"(i.e.":[159],"89.68%":[160],"Babble":[162],"noise":[163],"condition":[164],"at":[165],"5dB":[166],"SNR).":[167],"Lastly,":[168],"detailed":[172],"explanation":[173],"implementation":[176],"on-device":[178],"performance":[179],"(including":[180],"peak":[181],"power":[182],"consumption":[183],"metrics)":[184],"sets":[186],"work":[188,195],"apart":[189],"works.":[193],"This":[194],"has":[196],"notable":[198],"implications":[199],"improving":[201],"audio-processing":[203],"portable":[206],"battery-operated":[207],"Smart":[208],"loudspeakers":[209],"hearing":[211],"improvement":[212],"(HI)":[213],"devices.":[214]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}
