{"id":"https://openalex.org/W3081461453","doi":"https://doi.org/10.1109/taslp.2020.3019646","title":"Robust Source Counting and DOA Estimation Using Spatial Pseudo-Spectrum and Convolutional Neural Network","display_name":"Robust Source Counting and DOA Estimation Using Spatial Pseudo-Spectrum and Convolutional Neural Network","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3081461453","doi":"https://doi.org/10.1109/taslp.2020.3019646","mag":"3081461453"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2020.3019646","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.3019646","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,"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":"green","oa_url":"https://dr.ntu.edu.sg/bitstream/10356/144539/2/Robust%20Source%20Counting%20and%20DOA%20Estimation%20...pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039913415","display_name":"Thi Ngoc Tho Nguyen","orcid":"https://orcid.org/0000-0002-0210-6373"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Thi Ngoc Tho Nguyen","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, Nanyang Technological University, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-0210-6373","affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072584895","display_name":"Woon\u2010Seng Gan","orcid":"https://orcid.org/0000-0002-7143-1823"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Woon-Seng Gan","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, Nanyang Technological University, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-7143-1823","affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000819927","display_name":"Rishabh Ranjan","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Rishabh Ranjan","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, Nanyang Technological University, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5105462806","display_name":"Douglas L. Jones","orcid":"https://orcid.org/0000-0002-7817-7629"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Douglas L. Jones","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, Champaign, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, Champaign, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.8301,"has_fulltext":true,"cited_by_count":91,"citation_normalized_percentile":{"value":0.97838093,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"28","issue":null,"first_page":"2626","last_page":"2637"},"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/T11698","display_name":"Underwater Acoustics Research","score":0.9991999864578247,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9936000108718872,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7755639553070068},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5869460105895996},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5280017852783203},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43604880571365356},{"id":"https://openalex.org/keywords/spectrum","display_name":"Spectrum (functional analysis)","score":0.4320825934410095},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.4131471514701843},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32872408628463745},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.14857423305511475},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07999545335769653}],"concepts":[{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7755639553070068},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5869460105895996},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5280017852783203},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43604880571365356},{"id":"https://openalex.org/C156778621","wikidata":"https://www.wikidata.org/wiki/Q1365748","display_name":"Spectrum (functional analysis)","level":2,"score":0.4320825934410095},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.4131471514701843},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32872408628463745},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.14857423305511475},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07999545335769653},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2020.3019646","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.3019646","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,"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"},{"id":"pmh:oai:dr.ntu.edu.sg:10356/144539","is_oa":true,"landing_page_url":"https://hdl.handle.net/10356/144539","pdf_url":"https://dr.ntu.edu.sg/bitstream/10356/144539/2/Robust%20Source%20Counting%20and%20DOA%20Estimation%20...pdf","source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal Article"}],"best_oa_location":{"id":"pmh:oai:dr.ntu.edu.sg:10356/144539","is_oa":true,"landing_page_url":"https://hdl.handle.net/10356/144539","pdf_url":"https://dr.ntu.edu.sg/bitstream/10356/144539/2/Robust%20Source%20Counting%20and%20DOA%20Estimation%20...pdf","source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal Article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320766","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302"},{"id":"https://openalex.org/F4320327962","display_name":"Singapore Telecommunications Limited","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3081461453.pdf","grobid_xml":"https://content.openalex.org/works/W3081461453.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1494037697","https://openalex.org/W1494198834","https://openalex.org/W1603075283","https://openalex.org/W1964998538","https://openalex.org/W1969299255","https://openalex.org/W1993678034","https://openalex.org/W2061074721","https://openalex.org/W2066218102","https://openalex.org/W2068068201","https://openalex.org/W2113638573","https://openalex.org/W2128131274","https://openalex.org/W2139129402","https://openalex.org/W2151227854","https://openalex.org/W2161811374","https://openalex.org/W2222512263","https://openalex.org/W2561817999","https://openalex.org/W2586642235","https://openalex.org/W2672714283","https://openalex.org/W2763188033","https://openalex.org/W2772736377","https://openalex.org/W2775794021","https://openalex.org/W2885219692","https://openalex.org/W2917254586","https://openalex.org/W2931364255","https://openalex.org/W2942551338","https://openalex.org/W2964342924","https://openalex.org/W2982537717","https://openalex.org/W2998508940","https://openalex.org/W3098454764","https://openalex.org/W3105684258","https://openalex.org/W3139695047","https://openalex.org/W6667418930","https://openalex.org/W6676344012"],"related_works":["https://openalex.org/W2051487156","https://openalex.org/W2073681303","https://openalex.org/W4293226380","https://openalex.org/W2053286651","https://openalex.org/W2181743346","https://openalex.org/W2187401768","https://openalex.org/W4321487865","https://openalex.org/W2181413294","https://openalex.org/W4313906399","https://openalex.org/W2989452537"],"abstract_inverted_index":{"Many":[0],"signal":[1],"processing-based":[2],"methods":[3,89,171,176],"for":[4,90],"sound":[5,148,160],"source":[6,21],"direction-of-arrival":[7,81,91],"estimation":[8,82,92,175],"produce":[9],"a":[10,54,103],"spatial":[11,37,123],"pseudo-spectrum":[12],"of":[13,27,33,48,116,139,180,187],"which":[14,125],"the":[15,20,36,46,57,114,119,137,140,155,169],"local":[16],"maxima":[17],"strongly":[18],"indicate":[19],"directions.":[22],"Due":[23],"to":[24,64,73,96,101,111,143,158],"different":[25,31,97,178,185],"levels":[26,179],"noise,":[28],"reverberation":[29],"and":[30,80,118,150,153,164,182,184],"number":[32,47,115,186],"overlapping":[34],"sources,":[35],"pseudo-spectra":[38],"are":[39],"noisy":[40],"even":[41],"after":[42],"smoothing.":[43],"In":[44,85],"addition,":[45,86],"sources":[49,117],"is":[50,62],"often":[51],"unknown.":[52],"As":[53],"result,":[55],"selecting":[56],"peaks":[58],"from":[59,121,130],"these":[60],"spectra":[61],"susceptible":[63],"error.":[65],"Convolutional":[66],"neural":[67,106,141],"network":[68,107,142,156],"has":[69],"been":[70],"successfully":[71],"applied":[72],"many":[74],"image":[75],"processing":[76],"problems":[77],"in":[78,83,177],"general":[79],"particular.":[84],"deep":[87],"learning-based":[88],"show":[93,167],"good":[94],"generalization":[95],"environments.":[98],"We":[99],"propose":[100],"use":[102],"2D":[104],"convolutional":[105],"with":[108],"multi-task":[109],"learning":[110],"robustly":[112],"estimate":[113],"directions-of-arrival":[120],"short-time":[122],"pseudo-spectra,":[124],"have":[126],"useful":[127],"directional":[128,151],"information":[129],"audio":[131],"input":[132],"signals.":[133],"This":[134],"approach":[135],"reduces":[136],"tendency":[138],"learn":[144],"unwanted":[145],"association":[146],"between":[147],"classes":[149],"information,":[152],"helps":[154],"generalize":[157],"unseen":[159],"classes.":[161],"The":[162],"simulation":[163],"experimental":[165],"results":[166],"that":[168],"proposed":[170],"outperform":[172],"other":[173],"directional-of-arrival":[174],"noise":[181],"reverberation,":[183],"sources.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":24},{"year":2023,"cited_by_count":20},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}