{"id":"https://openalex.org/W2994067526","doi":"https://doi.org/10.1109/access.2019.2955049","title":"Real-Time Convolutional Neural Network-Based Speech Source Localization on Smartphone","display_name":"Real-Time Convolutional Neural Network-Based Speech Source Localization on Smartphone","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2994067526","doi":"https://doi.org/10.1109/access.2019.2955049","mag":"2994067526","pmid":"https://pubmed.ncbi.nlm.nih.gov/32754421"},"language":"en","primary_location":{"id":"doi:10.1109/access.2019.2955049","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2955049","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08910614.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/ielx7/6287639/8600701/08910614.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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","Department of Electrical and Computer Engineering, The University of Texas at Dallas, Richardson, 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":"Department of Electrical and Computer Engineering, The University of Texas at Dallas, Richardson, 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","Department of Electrical and Computer Engineering, The University of Texas at Dallas, Richardson, 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":"Department of Electrical and Computer Engineering, The University of Texas at Dallas, Richardson, USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","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","Department of Electrical and Computer Engineering, The University of Texas at Dallas, Richardson, 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":"Department of Electrical and Computer Engineering, The University of Texas at Dallas, Richardson, 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","Department of Electrical and Computer Engineering, The University of Texas at Dallas, Richardson, 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":"Department of Electrical and Computer Engineering, The University of Texas at Dallas, Richardson, 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":2.5047,"has_fulltext":true,"cited_by_count":23,"citation_normalized_percentile":{"value":0.90474162,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"7","issue":null,"first_page":"169969","last_page":"169978"},"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":0.9987000226974487,"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":0.9976999759674072,"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":0.902379035949707},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.8106483221054077},{"id":"https://openalex.org/keywords/android","display_name":"Android (operating system)","score":0.6581950187683105},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5595384836196899},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5239123106002808},{"id":"https://openalex.org/keywords/short-time-fourier-transform","display_name":"Short-time Fourier transform","score":0.49465081095695496},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.41815248131752014},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4114637076854706},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3721160888671875},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.21494024991989136}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.902379035949707},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.8106483221054077},{"id":"https://openalex.org/C557433098","wikidata":"https://www.wikidata.org/wiki/Q94","display_name":"Android (operating system)","level":2,"score":0.6581950187683105},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5595384836196899},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5239123106002808},{"id":"https://openalex.org/C166386157","wikidata":"https://www.wikidata.org/wiki/Q1477735","display_name":"Short-time Fourier transform","level":4,"score":0.49465081095695496},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.41815248131752014},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4114637076854706},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3721160888671875},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.21494024991989136},{"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/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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.2019.2955049","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2955049","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08910614.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:32754421","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/32754421","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:196c25dfd9034f8b93f339d5e80ecbde","is_oa":true,"landing_page_url":"https://doaj.org/article/196c25dfd9034f8b93f339d5e80ecbde","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 7, Pp 169969-169978 (2019)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:7402615","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7402615","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1109/access.2019.2955049","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2955049","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08910614.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":[{"id":"https://metadata.un.org/sdg/16","score":0.4000000059604645,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G7871880674","display_name":null,"funder_award_id":"1R01DC015430-04","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/F4320337352","display_name":"National Institute on Deafness and Other Communication Disorders","ror":"https://ror.org/04mhx6838"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2994067526.pdf","grobid_xml":"https://content.openalex.org/works/W2994067526.grobid-xml"},"referenced_works_count":48,"referenced_works":["https://openalex.org/W14578209","https://openalex.org/W61762298","https://openalex.org/W1603075283","https://openalex.org/W1665214252","https://openalex.org/W1975675577","https://openalex.org/W1977167953","https://openalex.org/W2020064670","https://openalex.org/W2046317813","https://openalex.org/W2061074721","https://openalex.org/W2097823155","https://openalex.org/W2113638573","https://openalex.org/W2114471793","https://openalex.org/W2114863372","https://openalex.org/W2123263496","https://openalex.org/W2137026380","https://openalex.org/W2151938450","https://openalex.org/W2160815625","https://openalex.org/W2163605009","https://openalex.org/W2251372956","https://openalex.org/W2403149086","https://openalex.org/W2486913545","https://openalex.org/W2611943505","https://openalex.org/W2626544737","https://openalex.org/W2701869962","https://openalex.org/W2755177320","https://openalex.org/W2757826220","https://openalex.org/W2776323726","https://openalex.org/W2784238911","https://openalex.org/W2793357660","https://openalex.org/W2798848987","https://openalex.org/W2898639684","https://openalex.org/W2898679241","https://openalex.org/W2899313078","https://openalex.org/W2899406861","https://openalex.org/W2899467190","https://openalex.org/W2938670253","https://openalex.org/W2947942791","https://openalex.org/W2950448225","https://openalex.org/W2963339453","https://openalex.org/W3104757150","https://openalex.org/W3104947433","https://openalex.org/W3208082774","https://openalex.org/W4249052411","https://openalex.org/W6600580371","https://openalex.org/W6637242042","https://openalex.org/W6644815614","https://openalex.org/W6674630822","https://openalex.org/W6684191040"],"related_works":["https://openalex.org/W2008311543","https://openalex.org/W2802845977","https://openalex.org/W2078793534","https://openalex.org/W2318109418","https://openalex.org/W2120847449","https://openalex.org/W3097412542","https://openalex.org/W2376615171","https://openalex.org/W2168274102","https://openalex.org/W4310813901","https://openalex.org/W1927135183"],"abstract_inverted_index":{"In":[0],"this":[1,110],"paper,":[2],"we":[3,114,172],"present":[4],"a":[5,31,191,198],"real-time":[6,116],"convolutional":[7],"neural":[8],"network":[9],"(CNN)":[10],"based":[11],"approach":[12],"for":[13,48,131,137,147,182,206],"speech":[14],"source":[15],"localization":[16],"(SSL)":[17],"using":[18,37],"Android-based":[19],"smartphone":[20,125,168],"and":[21,39,92,141,150],"its":[22],"two":[23],"built-in":[24],"microphones":[25],"under":[26],"noisy":[27,54],"conditions.":[28],"We":[29,51,76,158],"propose":[30],"new":[32],"input":[33],"feature":[34],"set":[35],"-":[36],"real":[38,66],"imaginary":[40],"parts":[41],"of":[42,65,109,118,194,197,203,210],"the":[43,78,178,195,201,208],"short-time":[44],"Fourier":[45],"transform":[46],"(STFT)":[47],"CNN-based":[49,83,96],"SSL.":[50],"use":[52,183],"simulated":[53],"data":[55],"from":[56],"popular":[57],"datasets":[58],"that":[59,86,94,113,160],"was":[60],"augmented":[61],"with":[62,126,184,212],"few":[63],"hours":[64],"recordings":[67],"collected":[68],"on":[69,89,102,122,200],"smartphones":[70,205],"to":[71,81,167,176],"train":[72],"our":[73,90,95,119,161],"CNN":[74,120,162],"model.":[75],"compare":[77],"proposed":[79,188],"method":[80,98],"recent":[82],"SSL":[84,97],"methods":[85],"are":[87],"trained":[88],"dataset":[91],"show":[93,159],"offers":[99],"higher":[100],"accuracy":[101,152],"identical":[103],"test":[104],"datasets.":[105],"Another":[106],"unique":[107],"aspect":[108],"work":[111],"is":[112,144,164],"perform":[115],"inferencing":[117],"model":[121,163,180],"an":[123],"Android":[124,204],"low":[127],"latency":[128],"(14":[129],"milliseconds(ms)":[130],"single":[132],"frame-based":[133,139],"estimation,":[134],"180":[135],"ms":[136,146],"multi":[138],"estimation":[140],"frame":[142],"length":[143],"20":[145],"both":[148],"cases)":[149],"high":[151],"(i.e.":[153],"88.83%":[154],"at":[155],"0dB":[156],"SNR).":[157],"rather":[165],"robust":[166],"hardware":[169],"mismatch,":[170],"hence":[171],"may":[173],"not":[174],"need":[175],"retrain":[177],"entire":[179],"again":[181],"different":[185],"smartphones.":[186],"The":[187],"application":[189],"provides":[190],"'visual'":[192],"indication":[193],"direction":[196],"talker":[199],"screen":[202],"improving":[207],"hearing":[209,213],"people":[211],"disorders.":[214]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":3}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}