{"id":"https://openalex.org/W4408352507","doi":"https://doi.org/10.1109/icassp49660.2025.10890474","title":"Robust Target Speaker Direction of Arrival Estimation","display_name":"Robust Target Speaker Direction of Arrival Estimation","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352507","doi":"https://doi.org/10.1109/icassp49660.2025.10890474"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890474","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890474","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100674834","display_name":"Zixuan Li","orcid":"https://orcid.org/0000-0003-0242-0984"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zixuan Li","raw_affiliation_strings":["Inner Mongolia University,College of Computer Science,Hohhot,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,College of Computer Science,Hohhot,China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103195569","display_name":"Shulin He","orcid":"https://orcid.org/0009-0002-0382-3515"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shulin He","raw_affiliation_strings":["Inner Mongolia University,College of Computer Science,Hohhot,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,College of Computer Science,Hohhot,China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100693230","display_name":"Xueliang Zhang","orcid":"https://orcid.org/0000-0002-0406-1105"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueliang Zhang","raw_affiliation_strings":["Inner Mongolia University,College of Computer Science,Hohhot,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,College of Computer Science,Hohhot,China","institution_ids":["https://openalex.org/I2722730"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2722730"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9955999851226807,"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":0.9955999851226807,"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/T10931","display_name":"Direction-of-Arrival Estimation Techniques","score":0.9825000166893005,"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/T10891","display_name":"Radar Systems and Signal Processing","score":0.9750999808311462,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"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/direction-of-arrival","display_name":"Direction of arrival","score":0.6518592834472656},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6465959548950195},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5149039030075073},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.4723331034183502},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.44510504603385925},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.19127798080444336},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11423173546791077}],"concepts":[{"id":"https://openalex.org/C172051844","wikidata":"https://www.wikidata.org/wiki/Q5280438","display_name":"Direction of arrival","level":3,"score":0.6518592834472656},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6465959548950195},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5149039030075073},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.4723331034183502},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.44510504603385925},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.19127798080444336},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11423173546791077},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890474","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890474","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1603075283","https://openalex.org/W1993678034","https://openalex.org/W2046317813","https://openalex.org/W2067295501","https://openalex.org/W2101609516","https://openalex.org/W2101658087","https://openalex.org/W2113638573","https://openalex.org/W2113744809","https://openalex.org/W2114863372","https://openalex.org/W2117678320","https://openalex.org/W2128131274","https://openalex.org/W2135431242","https://openalex.org/W2135817141","https://openalex.org/W2403149086","https://openalex.org/W2611943505","https://openalex.org/W2889442120","https://openalex.org/W2890996850","https://openalex.org/W2952218014","https://openalex.org/W2991361823","https://openalex.org/W3015372568","https://openalex.org/W3015623828","https://openalex.org/W3016252974","https://openalex.org/W3024869864","https://openalex.org/W3171278394","https://openalex.org/W4213377681","https://openalex.org/W4224919629","https://openalex.org/W4225905067","https://openalex.org/W4385245566","https://openalex.org/W4391621214","https://openalex.org/W4392903092","https://openalex.org/W6846436795"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"In":[0],"multi-speaker":[1,131],"environments":[2],"the":[3,31,60,64,83,86,91,121,147],"direction":[4],"of":[5,8,33,63,85],"arrival":[6],"(DOA)":[7],"a":[9,50,68,78,94,103,111],"target":[10,20,65,87],"speaker":[11,66,112],"is":[12,143],"key":[13],"for":[14,98,106,114],"improving":[15,100],"speech":[16,62,95,101],"clarity":[17],"and":[18,36,70,73,110,133],"extracting":[19,115],"speaker\u2019s":[21,88],"voice.":[22,89],"However,":[23],"traditional":[24],"DOA":[25,53,84],"estimation":[26,54],"methods":[27],"often":[28],"struggle":[29],"in":[30],"presence":[32],"noise,":[34],"reverberation,":[35],"particularly":[37],"when":[38],"competing":[39],"speakers":[40],"are":[41],"present.":[42],"To":[43],"address":[44],"these":[45],"challenges,":[46],"we":[47],"propose":[48],"RTS-DOA,":[49],"robust":[51],"real-time":[52],"system.":[55],"This":[56],"system":[57,92,128],"innovatively":[58],"uses":[59],"registered":[61],"as":[67],"reference":[69],"leverages":[71],"full-band":[72],"sub-band":[74],"spectral":[75],"information":[76],"from":[77],"microphone":[79],"array":[80],"to":[81],"estimate":[82],"Specifically,":[90],"comprises":[93],"enhancement":[96],"module":[97,105,113],"initially":[99],"quality,":[102],"spatial":[104,108],"learning":[107],"information,":[109],"voiceprint":[116],"features.":[117],"Experimental":[118],"results":[119],"on":[120],"LibriSpeech":[122],"dataset":[123],"demonstrate":[124],"that":[125,142],"our":[126],"RTS-DOA":[127],"effectively":[129],"tackles":[130],"scenarios":[132],"established":[134],"new":[135],"optimal":[136],"benchmarks,":[137],"achieving":[138],"an":[139],"Accuracy":[140],"Rate":[141],"0.31":[144],"higher":[145],"than":[146],"baseline.":[148]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}