{"id":"https://openalex.org/W4375869077","doi":"https://doi.org/10.1109/icassp49357.2023.10095551","title":"GCC-Speaker: Target Speaker Localization with Optimal Speaker-Dependent Weighting in Multi-Speaker Scenarios","display_name":"GCC-Speaker: Target Speaker Localization with Optimal Speaker-Dependent Weighting in Multi-Speaker Scenarios","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869077","doi":"https://doi.org/10.1109/icassp49357.2023.10095551"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095551","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095551","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5101679484","display_name":"Guanjun Li","orcid":"https://orcid.org/0000-0002-8200-5360"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanjun Li","raw_affiliation_strings":["Chinese Academy of Sciences,NLPR, Institute of Automation,China","NLPR, Institute of Automation, Chinese Academy of Sciences, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,NLPR, Institute of Automation,China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"NLPR, Institute of Automation, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100652844","display_name":"Wei Xue","orcid":"https://orcid.org/0000-0002-4942-7748"},"institutions":[{"id":"https://openalex.org/I141568987","display_name":"Hong Kong Baptist University","ror":"https://ror.org/0145fw131","country_code":"HK","type":"education","lineage":["https://openalex.org/I141568987"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Wei Xue","raw_affiliation_strings":["Hong Kong Baptist University,Department of Computer Science,Hong Kong SAR,China","Department of Computer Science, Hong Kong Baptist University, Hong Kong SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong Baptist University,Department of Computer Science,Hong Kong SAR,China","institution_ids":["https://openalex.org/I141568987"]},{"raw_affiliation_string":"Department of Computer Science, Hong Kong Baptist University, Hong Kong SAR, China","institution_ids":["https://openalex.org/I141568987"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039635290","display_name":"Wenju Liu","orcid":"https://orcid.org/0000-0001-9088-8282"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenju Liu","raw_affiliation_strings":["Chinese Academy of Sciences,NLPR, Institute of Automation,China","NLPR, Institute of Automation, Chinese Academy of Sciences, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,NLPR, Institute of Automation,China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"NLPR, Institute of Automation, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078525423","display_name":"Jiangyan Yi","orcid":"https://orcid.org/0000-0003-2422-4618"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangyan Yi","raw_affiliation_strings":["Chinese Academy of Sciences,NLPR, Institute of Automation,China","NLPR, Institute of Automation, Chinese Academy of Sciences, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,NLPR, Institute of Automation,China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"NLPR, Institute of Automation, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112613657","display_name":"Jianhua Tao","orcid":"https://orcid.org/0000-0002-9344-6428"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianhua Tao","raw_affiliation_strings":["Tsinghua University,Department of Automation","Department of Automation, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Automation","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Automation, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"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":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":0.9990000128746033,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9983999729156494,"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/weighting","display_name":"Weighting","score":0.8267338275909424},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6865650415420532},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6686125993728638},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.6607170701026917},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6594494581222534},{"id":"https://openalex.org/keywords/a-weighting","display_name":"A-weighting","score":0.5527005195617676},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.5193277597427368},{"id":"https://openalex.org/keywords/interference","display_name":"Interference (communication)","score":0.4813719391822815},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.44227585196495056},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.4320133328437805},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.38217321038246155},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.328786164522171},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.26551395654678345},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.13355639576911926},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10856053233146667},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06020823121070862}],"concepts":[{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.8267338275909424},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6865650415420532},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6686125993728638},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.6607170701026917},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6594494581222534},{"id":"https://openalex.org/C70136482","wikidata":"https://www.wikidata.org/wiki/Q13583781","display_name":"A-weighting","level":3,"score":0.5527005195617676},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.5193277597427368},{"id":"https://openalex.org/C32022120","wikidata":"https://www.wikidata.org/wiki/Q797225","display_name":"Interference (communication)","level":3,"score":0.4813719391822815},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.44227585196495056},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.4320133328437805},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38217321038246155},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.328786164522171},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26551395654678345},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.13355639576911926},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10856053233146667},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06020823121070862},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095551","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095551","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-136976","is_oa":false,"landing_page_url":"https://repository.hkust.edu.hk/ir/Record/1783.1-136976","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W174187144","https://openalex.org/W1522301498","https://openalex.org/W1987906574","https://openalex.org/W2009153891","https://openalex.org/W2024490156","https://openalex.org/W2043216213","https://openalex.org/W2046317813","https://openalex.org/W2113638573","https://openalex.org/W2320444803","https://openalex.org/W2532891002","https://openalex.org/W2533459608","https://openalex.org/W2568308529","https://openalex.org/W2701869962","https://openalex.org/W2749510669","https://openalex.org/W2889061314","https://openalex.org/W2889426390","https://openalex.org/W2897977894","https://openalex.org/W2900582271","https://openalex.org/W2938511859","https://openalex.org/W2938670253","https://openalex.org/W2951130829","https://openalex.org/W2962866211","https://openalex.org/W2972757492","https://openalex.org/W2973167466","https://openalex.org/W2973179291","https://openalex.org/W4312314094","https://openalex.org/W6631190155"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W66821593","https://openalex.org/W2149220986","https://openalex.org/W1521299571","https://openalex.org/W1493012537","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W3141593045","https://openalex.org/W2144470400","https://openalex.org/W2911612049"],"abstract_inverted_index":{"Existing":[0],"noise-robust":[1],"and":[2,33,56,69,102,140],"reverberant-robust":[3],"localization":[4,38,88,132],"algorithms":[5,133],"fail":[6],"to":[7,82,109,112,127],"localize":[8],"the":[9,22,27,45,48,79,84,92,97,103,122,128],"target":[10,28,36,86,130],"speaker":[11,29,37,87,131],"when":[12],"interfering":[13],"speakers":[14],"are":[15],"present.":[16],"In":[17],"this":[18],"paper,":[19],"we":[20,43,95],"address":[21],"problem":[23],"of":[24,47,106,124],"localizing":[25],"only":[26],"in":[30],"multi-speaker":[31],"scenarios":[32],"propose":[34,57],"a":[35,64],"algorithm,":[39],"called":[40],"GCC-speaker.":[41],"Specifically,":[42],"modify":[44],"weighting":[46,61,74],"generalized":[49],"cross-correlation":[50],"with":[51],"phase":[52],"transform":[53],"(GCC-PHAT)":[54],"algorithm":[55,81],"an":[58],"optimal":[59,85],"speaker-dependent":[60,73],"based":[62],"on":[63],"novel":[65],"localization-related":[66],"loss":[67,93],"function":[68],"data-driven":[70],"training.":[71],"The":[72,118],"is":[75],"responsible":[76],"for":[77,91,134],"guiding":[78],"GCC":[80,99],"obtain":[83],"results.":[89],"As":[90],"function,":[94],"constrain":[96],"estimated":[98,104],"angular":[100],"spectrum":[101],"direction":[105],"arrival":[107],"(DOA)":[108],"be":[110],"close":[111],"their":[113],"ground":[114],"truth":[115],"values,":[116],"respectively.":[117],"experimental":[119],"results":[120],"show":[121],"superiority":[123],"GCC-speaker":[125],"compared":[126],"existing":[129],"different":[135],"signal-to-interference":[136],"ratios,":[137],"reverberation":[138],"times":[139],"array":[141],"geometries.":[142]},"counts_by_year":[{"year":2025,"cited_by_count":5}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
