{"id":"https://openalex.org/W3113264499","doi":"https://doi.org/10.1109/taslp.2020.3043107","title":"Estimation Reliability Function Assisted Sound Source Localization With Enhanced Steering Vector Phase Difference","display_name":"Estimation Reliability Function Assisted Sound Source Localization With Enhanced Steering Vector Phase Difference","publication_year":2020,"publication_date":"2020-12-09","ids":{"openalex":"https://openalex.org/W3113264499","doi":"https://doi.org/10.1109/taslp.2020.3043107","mag":"3113264499"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2020.3043107","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.3043107","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011611391","display_name":"Longbiao Cheng","orcid":"https://orcid.org/0000-0002-0635-1480"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Longbiao Cheng","raw_affiliation_strings":["Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101770379","display_name":"Xingwei Sun","orcid":"https://orcid.org/0000-0002-9382-6113"},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingwei Sun","raw_affiliation_strings":["Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102802382","display_name":"Dingding Yao","orcid":"https://orcid.org/0000-0002-9610-8782"},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dingding Yao","raw_affiliation_strings":["Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100450058","display_name":"Junfeng Li","orcid":"https://orcid.org/0000-0002-6272-9169"},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junfeng Li","raw_affiliation_strings":["Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100425112","display_name":"Yonghong Yan","orcid":"https://orcid.org/0000-0001-6907-5770"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]},{"id":"https://openalex.org/I4210106108","display_name":"Xinjiang Technical Institute of Physics & Chemistry","ror":"https://ror.org/00x44h034","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210106108"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yonghong Yan","raw_affiliation_strings":["Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China","Xinjiang Key Laboratory of Minority Speech and Language Information Processing, Xinjiang Technical Institute of Physics and Chemistry, Chinese Academy of Sciences, Xinjiang, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Xinjiang Key Laboratory of Minority Speech and Language Information Processing, Xinjiang Technical Institute of Physics and Chemistry, Chinese Academy of Sciences, Xinjiang, China","institution_ids":["https://openalex.org/I4210106108","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5011611391"],"corresponding_institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.6061,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.68183015,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":"29","issue":null,"first_page":"421","last_page":"435"},"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":0.9980000257492065,"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":0.996399998664856,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6774742007255554},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6589033603668213},{"id":"https://openalex.org/keywords/direction-of-arrival","display_name":"Direction of arrival","score":0.6110036969184875},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5207262635231018},{"id":"https://openalex.org/keywords/mean-squared-error","display_name":"Mean squared error","score":0.47258102893829346},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.44210225343704224},{"id":"https://openalex.org/keywords/histogram","display_name":"Histogram","score":0.4226635694503784},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.39934468269348145},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3490599989891052},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.348915696144104},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33136609196662903},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21111315488815308},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09460172057151794},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.07442152500152588}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6774742007255554},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6589033603668213},{"id":"https://openalex.org/C172051844","wikidata":"https://www.wikidata.org/wiki/Q5280438","display_name":"Direction of arrival","level":3,"score":0.6110036969184875},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5207262635231018},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.47258102893829346},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.44210225343704224},{"id":"https://openalex.org/C53533937","wikidata":"https://www.wikidata.org/wiki/Q185020","display_name":"Histogram","level":3,"score":0.4226635694503784},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39934468269348145},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3490599989891052},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.348915696144104},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33136609196662903},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21111315488815308},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09460172057151794},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.07442152500152588},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/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.2020.3043107","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.3043107","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"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6399999856948853,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1876158985","display_name":null,"funder_award_id":"11722437","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3242532954","display_name":null,"funder_award_id":"2017YFB1002803","funder_id":"https://openalex.org/F4320336026","funder_display_name":"National Key Research and Development Program of China Stem Cell and Translational Research"},{"id":"https://openalex.org/G7500731927","display_name":null,"funder_award_id":"11674352","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320336026","display_name":"National Key Research and Development Program of China Stem Cell and Translational Research","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1971405469","https://openalex.org/W1974387177","https://openalex.org/W1996304098","https://openalex.org/W2005733316","https://openalex.org/W2018205510","https://openalex.org/W2021196544","https://openalex.org/W2044893557","https://openalex.org/W2045352743","https://openalex.org/W2046317813","https://openalex.org/W2063521662","https://openalex.org/W2069681747","https://openalex.org/W2087873531","https://openalex.org/W2089586791","https://openalex.org/W2101856597","https://openalex.org/W2113638573","https://openalex.org/W2116635162","https://openalex.org/W2117678320","https://openalex.org/W2128562854","https://openalex.org/W2132920253","https://openalex.org/W2134533334","https://openalex.org/W2141884927","https://openalex.org/W2296167893","https://openalex.org/W2399877729","https://openalex.org/W2403407569","https://openalex.org/W2509298024","https://openalex.org/W2548487638","https://openalex.org/W2616139854","https://openalex.org/W2701869962","https://openalex.org/W2749335474","https://openalex.org/W2765962757","https://openalex.org/W2772734659","https://openalex.org/W2884424734","https://openalex.org/W2897977894","https://openalex.org/W2924657680","https://openalex.org/W2937324313","https://openalex.org/W2938670253","https://openalex.org/W2947942791","https://openalex.org/W2962866211","https://openalex.org/W2963339453","https://openalex.org/W2979827043","https://openalex.org/W3101162615","https://openalex.org/W6679438253","https://openalex.org/W6712828188","https://openalex.org/W6769176809"],"related_works":["https://openalex.org/W2107628111","https://openalex.org/W2394004323","https://openalex.org/W2102148524","https://openalex.org/W2398764543","https://openalex.org/W2027335291","https://openalex.org/W4210328553","https://openalex.org/W2770593030","https://openalex.org/W3154990682","https://openalex.org/W2560201613","https://openalex.org/W2314720829"],"abstract_inverted_index":{"The":[0,55,82,108],"performance":[1],"of":[2,70,85,110,129],"the":[3,28,47,68,71,86,101,111,118,137,141],"traditional":[4],"direction-of-arrival":[5],"(DOA)":[6],"estimation":[7,60],"algorithms":[8,146],"greatly":[9],"degrades":[10],"in":[11,31,147],"noisy":[12],"and":[13,26,58,127,131,149],"reverberant":[14,133],"environments.":[15],"Recently,":[16],"deep":[17,48,78],"learning":[18],"has":[19],"been":[20],"applied":[21],"to":[22],"sound":[23,42,112,143],"source":[24,43,113,144],"localization":[25,44,145],"provided":[27],"substantial":[29],"improvement":[30],"robustness":[32],"for":[33],"DOA":[34,109,151],"estimation.":[35,152],"In":[36],"this":[37],"paper,":[38],"we":[39],"propose":[40],"a":[41,93],"approach":[45,139],"using":[46,77],"learning-based":[49],"steering":[50,56,87],"vector":[51],"phase":[52,83],"difference":[53,84],"enhancement.":[54],"vectors":[57,88],"their":[59],"reliability":[61],"functions":[62],"(ERFs)":[63],"are":[64,75],"first":[65],"estimated":[66],"under":[67],"guidance":[69],"time-frequency":[72],"masks":[73],"that":[74,136],"predicted":[76],"neural":[79],"network":[80],"(DNN).":[81],"is":[89,98,114],"further":[90],"enhanced":[91],"with":[92,100,124],"second":[94],"DNN":[95],"model,":[96],"which":[97],"trained":[99],"ERF-weighted":[102,119],"mean":[103],"square":[104],"error":[105],"(MSE)":[106],"loss.":[107],"finally":[115],"determined":[116],"by":[117],"histogram":[120],"analysis.":[121],"Experimental":[122],"results":[123],"various":[125,132],"types":[126],"levels":[128],"noise":[130],"conditions":[134],"show":[135],"proposed":[138],"outperforms":[140],"state-of-the-art":[142],"utterance":[148],"frame-level":[150]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
