{"id":"https://openalex.org/W4392908923","doi":"https://doi.org/10.1109/icassp48485.2024.10447143","title":"LOCSELECT: Target Speaker Localization with an Auditory Selective Hearing Mechanism","display_name":"LOCSELECT: Target Speaker Localization with an Auditory Selective Hearing Mechanism","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392908923","doi":"https://doi.org/10.1109/icassp48485.2024.10447143"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447143","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447143","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5107249182","display_name":"Yu Chen","orcid":"https://orcid.org/0009-0004-5272-6193"},"institutions":[{"id":"https://openalex.org/I4210099586","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099586"]},{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]},{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Chen","raw_affiliation_strings":["University of Science and Technology Beijing (USTB),School of Computer and Communication Engineering,China","Shenzhen Research Institute of Big Data, School of Data Science, The Chinese University of Hong Kong, Shenzhen, China","School of Computer and Communication Engineering, University of Science and Technology Beijing (USTB), China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology Beijing (USTB),School of Computer and Communication Engineering,China","institution_ids":["https://openalex.org/I92403157"]},{"raw_affiliation_string":"Shenzhen Research Institute of Big Data, School of Data Science, The Chinese University of Hong Kong, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924","https://openalex.org/I4210099586"]},{"raw_affiliation_string":"School of Computer and Communication Engineering, University of Science and Technology Beijing (USTB), China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056495776","display_name":"Xinyuan Qian","orcid":"https://orcid.org/0000-0002-9511-6713"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyuan Qian","raw_affiliation_strings":["University of Science and Technology Beijing (USTB),School of Computer and Communication Engineering,China","School of Computer and Communication Engineering, University of Science and Technology Beijing (USTB), China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology Beijing (USTB),School of Computer and Communication Engineering,China","institution_ids":["https://openalex.org/I92403157"]},{"raw_affiliation_string":"School of Computer and Communication Engineering, University of Science and Technology Beijing (USTB), China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060530570","display_name":"Zexu Pan","orcid":"https://orcid.org/0000-0002-8106-1176"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zexu Pan","raw_affiliation_strings":["National University of Singapore,Singapore","National University of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056322023","display_name":"Kainan Chen","orcid":"https://orcid.org/0000-0002-7231-2404"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kainan Chen","raw_affiliation_strings":["Eigenspace GmbH,Germany","Eigenspace GmbH, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eigenspace GmbH,Germany","institution_ids":[]},{"raw_affiliation_string":"Eigenspace GmbH, Germany","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]},{"id":"https://openalex.org/I4210099586","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099586"]},{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["The Chinese University of Hong Kong,Shenzhen Research Institute of Big Data, School of Data Science,Shenzhen,China","Shenzhen Research Institute of Big Data, School of Data Science, The Chinese University of Hong Kong, Shenzhen, China","National University of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Shenzhen Research Institute of Big Data, School of Data Science,Shenzhen,China","institution_ids":["https://openalex.org/I4210116924","https://openalex.org/I4210099586"]},{"raw_affiliation_string":"Shenzhen Research Institute of Big Data, School of Data Science, The Chinese University of Hong Kong, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924","https://openalex.org/I4210099586"]},{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"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":"8696","last_page":"8700"},"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":0.9998999834060669,"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/T11698","display_name":"Underwater Acoustics Research","score":0.9977999925613403,"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/spectrogram","display_name":"Spectrogram","score":0.8912831544876099},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8043109178543091},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7419324517250061},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.636538028717041},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.488205224275589},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4431134760379791},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.41623252630233765},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35299402475357056},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3219979703426361},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.19754177331924438},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.16492244601249695}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8912831544876099},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8043109178543091},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7419324517250061},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.636538028717041},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.488205224275589},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4431134760379791},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.41623252630233765},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35299402475357056},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3219979703426361},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.19754177331924438},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.16492244601249695},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447143","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447143","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2799040894","display_name":null,"funder_award_id":"62271432","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5088964179","display_name":null,"funder_award_id":"T00120220002","funder_id":"https://openalex.org/F4320331102","funder_display_name":"Shenzhen Research Institute of Big Data"},{"id":"https://openalex.org/G6648122539","display_name":null,"funder_award_id":"62306029","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G861645084","display_name":null,"funder_award_id":"B10120210117-KP02","funder_id":"https://openalex.org/F4320322942","funder_display_name":"Chinese University of Hong Kong"}],"funders":[{"id":"https://openalex.org/F4320316083","display_name":"Tencent","ror":"https://ror.org/00hhjss72"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322942","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48"},{"id":"https://openalex.org/F4320325365","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993"},{"id":"https://openalex.org/F4320331102","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89"},{"id":"https://openalex.org/F4320333998","display_name":"Shenzhen Research Institute, City University of Hong Kong","ror":"https://ror.org/00xc0ma20"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1836465849","https://openalex.org/W2046317813","https://openalex.org/W2113638573","https://openalex.org/W2117505065","https://openalex.org/W2194775991","https://openalex.org/W2611943505","https://openalex.org/W2701869962","https://openalex.org/W2726515241","https://openalex.org/W2772736377","https://openalex.org/W2883288608","https://openalex.org/W2889061314","https://openalex.org/W2889426390","https://openalex.org/W2891627435","https://openalex.org/W2898268964","https://openalex.org/W2900582271","https://openalex.org/W2942551338","https://openalex.org/W2964342924","https://openalex.org/W2973062255","https://openalex.org/W2973167466","https://openalex.org/W3098454764","https://openalex.org/W3104196160","https://openalex.org/W3104757150","https://openalex.org/W3105684258","https://openalex.org/W3132182240","https://openalex.org/W3162475350","https://openalex.org/W3163206520","https://openalex.org/W3205596865","https://openalex.org/W3211178721","https://openalex.org/W4312367758","https://openalex.org/W4372260442","https://openalex.org/W6631190155","https://openalex.org/W6637242042"],"related_works":["https://openalex.org/W2897924318","https://openalex.org/W2138997758","https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W4313854686","https://openalex.org/W321304764","https://openalex.org/W2249138175","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W289407349"],"abstract_inverted_index":{"The":[0],"prevailing":[1],"noise-resistant":[2],"and":[3,10,116],"reverberation-resistant":[4],"localization":[5,35],"algorithms":[6,90],"primarily":[7],"emphasize":[8],"separating":[9],"providing":[11],"directional":[12],"output":[13],"for":[14,91],"each":[15],"speaker":[16,34],"in":[17],"multi-speaker":[18],"scenarios,":[19],"without":[20],"association":[21],"with":[22,37],"the":[23,47,72,77,82],"identity":[24],"of":[25,46,84,114,120],"speakers.":[26],"In":[27],"this":[28],"paper,":[29],"we":[30,50],"present":[31],"a":[32,38,43,53,63,109],"target":[33,48,73],"algorithm":[36],"selective":[39],"hearing":[40],"mechanism.":[41],"Given":[42],"reference":[44],"speech":[45],"speaker,":[49],"first":[51],"produce":[52],"speaker-dependent":[54],"spectrogram":[55],"mask":[56],"to":[57,70],"eliminate":[58],"interfering":[59],"speakers\u2019":[60],"speech.":[61],"Subsequently,":[62],"Long-Short-Term":[64],"Memory":[65],"(LSTM)":[66],"network":[67,106],"is":[68],"employed":[69],"extract":[71],"speaker\u2019s":[74],"location":[75],"from":[76],"filtered":[78],"spectrogram.":[79],"Experiments":[80],"validate":[81],"superiority":[83],"our":[85,104],"proposed":[86,105],"method":[87],"over":[88],"existing":[89],"different":[92],"scale-invariant":[93],"signal-to-noise":[94],"ratios":[95],"(SNR)":[96],"conditions.":[97],"Specifically,":[98],"at":[99],"SNR":[100],"=":[101],"-10":[102],"dB,":[103],"LocSelect":[107],"achieves":[108],"mean":[110],"absolute":[111],"error":[112],"(MAE)":[113],"3.55\u00b0":[115],"an":[117],"accuracy":[118],"(ACC)":[119],"87.40%.":[121]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
