{"id":"https://openalex.org/W4224918929","doi":"https://doi.org/10.1109/icassp43922.2022.9746221","title":"L-SpEx: Localized Target Speaker Extraction","display_name":"L-SpEx: Localized Target Speaker Extraction","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224918929","doi":"https://doi.org/10.1109/icassp43922.2022.9746221"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746221","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746221","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-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/A5071074013","display_name":"Meng Ge","orcid":"https://orcid.org/0000-0003-2017-4529"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]},{"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":["CN","SG"],"is_corresponding":true,"raw_author_name":"Meng Ge","raw_affiliation_strings":["Tianjin University,College of Intelligence and Computing,Tianjin,China","College of Intelligence and Computing, Tianjin University, Tianjin, China","Department of Electrical and Computer Engineering, National University of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University,College of Intelligence and Computing,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103210439","display_name":"Chenglin Xu","orcid":"https://orcid.org/0000-0002-1584-6282"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenglin Xu","raw_affiliation_strings":["Kuaishou Technology,Beijing,China","Kuaishou Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou Technology,Beijing,China","institution_ids":["https://openalex.org/I4401726859"]},{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101745213","display_name":"Longbiao Wang","orcid":"https://orcid.org/0000-0002-8094-6861"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longbiao Wang","raw_affiliation_strings":["Tianjin University,College of Intelligence and Computing,Tianjin,China","College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University,College of Intelligence and Computing,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070872826","display_name":"Eng Siong Chng","orcid":"https://orcid.org/0000-0001-6257-7399"},"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":"Eng Siong Chng","raw_affiliation_strings":["Nanyang Technological University,School of Computer Science and Engineering,Singapore","School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,School of Computer Science and Engineering,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017251198","display_name":"Jianwu Dang","orcid":"https://orcid.org/0000-0002-9237-4821"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]},{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN","JP"],"is_corresponding":false,"raw_author_name":"Jianwu Dang","raw_affiliation_strings":["Tianjin University,College of Intelligence and Computing,Tianjin,China","College of Intelligence and Computing, Tianjin University, Tianjin, China","Japan Advanced Institute of Science and Technology, Ishikawa, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University,College of Intelligence and Computing,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology, Ishikawa, Japan","institution_ids":["https://openalex.org/I177738480"]}]},{"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/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":["National University of Singapore,Department of Electrical and Computer Engineering,Singapore","The Chinese University of Hong Kong, Shenzhen, China","Department of Electrical and Computer Engineering, National University of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Department of Electrical and Computer Engineering,Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5071074013"],"corresponding_institution_ids":["https://openalex.org/I162868743","https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":3.0356,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.93673277,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7287","last_page":"7291"},"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":0.9994999766349792,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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/computer-science","display_name":"Computer science","score":0.7227684259414673},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7042151689529419},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5770122408866882},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.5507005453109741},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5416430234909058},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5184773802757263},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.47979313135147095},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.476752370595932},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4273311495780945},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39498376846313477},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.090648353099823}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7227684259414673},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7042151689529419},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5770122408866882},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.5507005453109741},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5416430234909058},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5184773802757263},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.47979313135147095},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.476752370595932},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4273311495780945},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39498376846313477},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.090648353099823}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746221","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746221","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1991139021","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2810934215","https://openalex.org/W2900893004","https://openalex.org/W2909607850","https://openalex.org/W2952218014","https://openalex.org/W2972802573","https://openalex.org/W2973054998","https://openalex.org/W3008762051","https://openalex.org/W3011424113","https://openalex.org/W3015199127","https://openalex.org/W3015788098","https://openalex.org/W3016361963","https://openalex.org/W3095312989","https://openalex.org/W3096073522","https://openalex.org/W3096571892","https://openalex.org/W3097653961","https://openalex.org/W3099330747","https://openalex.org/W3103434036","https://openalex.org/W3105169251","https://openalex.org/W3132182240","https://openalex.org/W3190394743","https://openalex.org/W6768815455","https://openalex.org/W6779752190"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2767892728","https://openalex.org/W2162158162","https://openalex.org/W4235705411","https://openalex.org/W1521299571","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W2175373321","https://openalex.org/W1998549096","https://openalex.org/W2144470400"],"abstract_inverted_index":{"Speaker":[0],"extraction":[1,24,70],"aims":[2],"to":[3,91,117,123],"extract":[4,92],"the":[5,27,32,40,87,93,100,107,124,129,142],"target":[6,33,41,68,88,101,111,125],"speaker\u2019s":[7,42,89,112],"voice":[8],"from":[9,26],"a":[10,82,119],"multi-talker":[11],"speech":[12,73],"mixture":[13],"given":[14],"an":[15,51,65],"auxiliary":[16],"reference":[17],"utterance.":[18],"Recent":[19],"studies":[20,37],"show":[21,135],"that":[22,39,75,136],"speaker":[23,69,83,102],"benefits":[25],"location":[28,43],"or":[29,48,58],"direction":[30],"of":[31,99],"speaker.":[34,126],"However,":[35],"these":[36],"assume":[38],"is":[44,76],"known":[45],"in":[46],"advance":[47],"detected":[49],"by":[50,86],"extra":[52],"visual":[53],"cue,":[54],"e.g.,":[55],"face":[56],"image":[57],"video.":[59],"In":[60],"this":[61],"paper,":[62],"we":[63,80],"propose":[64],"end-to-end":[66],"localized":[67],"on":[71,128],"pure":[72],"cues,":[74],"called":[77,133],"L-SpEx.":[78],"Specifically,":[79],"design":[81],"localizer":[84],"driven":[85],"embedding":[90,113],"spatial":[94,108],"features,":[95],"including":[96],"direction-of-arrival":[97],"(DOA)":[98],"and":[103,110],"beamforming":[104],"output.":[105],"Then,":[106],"cues":[109],"are":[114],"both":[115],"used":[116],"form":[118],"top-down":[120],"auditory":[121],"attention":[122],"Experiments":[127],"multi-channel":[130],"reverberant":[131],"dataset":[132],"MCLibri2Mix":[134],"our":[137],"L-SpEx":[138],"approach":[139],"significantly":[140],"outperforms":[141],"baseline":[143],"system.":[144]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":4}],"updated_date":"2026-05-02T08:42:23.175194","created_date":"2025-10-10T00:00:00"}
