{"id":"https://openalex.org/W4319862205","doi":"https://doi.org/10.1109/slt54892.2023.10023036","title":"LiMuSE: Lightweight Multi-Modal Speaker Extraction","display_name":"LiMuSE: Lightweight Multi-Modal Speaker Extraction","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862205","doi":"https://doi.org/10.1109/slt54892.2023.10023036"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10023036","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/slt54892.2023.10023036","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":"2022 IEEE Spoken Language Technology Workshop (SLT)","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/A5100414762","display_name":"Qinghua Liu","orcid":"https://orcid.org/0000-0003-4726-5797"},"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/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":"Qinghua Liu","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences (CASIA),Beijing,China","Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China","Qiushi Honors College, Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences (CASIA),Beijing,China","institution_ids":["https://openalex.org/I4210112150"]},{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"Qiushi Honors College, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031511677","display_name":"Yating Huang","orcid":"https://orcid.org/0000-0002-7822-1407"},"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"]},{"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":"Yating Huang","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences (CASIA),Beijing,China","Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China","School of Future Technology, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences (CASIA),Beijing,China","institution_ids":["https://openalex.org/I4210112150"]},{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"School of Future Technology, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059162334","display_name":"Yunzhe Hao","orcid":"https://orcid.org/0000-0001-7824-6965"},"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"]},{"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":"Yunzhe Hao","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences (CASIA),Beijing,China","Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China","School of Future Technology, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences (CASIA),Beijing,China","institution_ids":["https://openalex.org/I4210112150"]},{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"School of Future Technology, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101746187","display_name":"Jiaming Xu","orcid":"https://orcid.org/0000-0001-7635-1059"},"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"]},{"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":"Jiaming Xu","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences (CASIA),Beijing,China","Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China","School of Future Technology, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences (CASIA),Beijing,China","institution_ids":["https://openalex.org/I4210112150"]},{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"School of Future Technology, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108642431","display_name":"Bo Xu","orcid":"https://orcid.org/0000-0002-1111-1529"},"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"]},{"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":"Bo Xu","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences (CASIA),Beijing,China","Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China","School of Future Technology, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences (CASIA),Beijing,China","institution_ids":["https://openalex.org/I4210112150"]},{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"School of Future Technology, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2417,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.35485005,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"86","issue":null,"first_page":"488","last_page":"495"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7826569080352783},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.4852178394794464},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.46311038732528687},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4438944458961487},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.43722689151763916},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.42908334732055664},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.42840576171875},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3983294367790222},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13196781277656555},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.09893804788589478}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7826569080352783},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4852178394794464},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.46311038732528687},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4438944458961487},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.43722689151763916},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.42908334732055664},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.42840576171875},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3983294367790222},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13196781277656555},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.09893804788589478},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt54892.2023.10023036","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/slt54892.2023.10023036","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4583646794","display_name":null,"funder_award_id":"2021ZD0201500","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W1677182931","https://openalex.org/W2015143272","https://openalex.org/W2194775991","https://openalex.org/W2300242332","https://openalex.org/W2460742184","https://openalex.org/W2469490737","https://openalex.org/W2515770085","https://openalex.org/W2551572271","https://openalex.org/W2558649592","https://openalex.org/W2559655401","https://openalex.org/W2741151796","https://openalex.org/W2752782242","https://openalex.org/W2808631503","https://openalex.org/W2809624076","https://openalex.org/W2890952074","https://openalex.org/W2895807593","https://openalex.org/W2944851425","https://openalex.org/W2952218014","https://openalex.org/W2959214850","https://openalex.org/W2963163009","https://openalex.org/W2963290645","https://openalex.org/W2964016283","https://openalex.org/W2964233199","https://openalex.org/W2973179291","https://openalex.org/W2982456909","https://openalex.org/W3008400075","https://openalex.org/W3011424113","https://openalex.org/W3015372568","https://openalex.org/W3015783745","https://openalex.org/W3016361963","https://openalex.org/W3096090308","https://openalex.org/W3099330747","https://openalex.org/W3103434036","https://openalex.org/W3110852964","https://openalex.org/W3124666641","https://openalex.org/W3160464260","https://openalex.org/W3161305977","https://openalex.org/W3162534564","https://openalex.org/W3162539493","https://openalex.org/W3163114796","https://openalex.org/W3163287738","https://openalex.org/W3201437620","https://openalex.org/W4285737630","https://openalex.org/W4289665794","https://openalex.org/W4297775537","https://openalex.org/W6631190155","https://openalex.org/W6638523607","https://openalex.org/W6639703010","https://openalex.org/W6720242923","https://openalex.org/W6737664043","https://openalex.org/W6748319235","https://openalex.org/W6769802879","https://openalex.org/W6770625286","https://openalex.org/W6789284391"],"related_works":["https://openalex.org/W3161919736","https://openalex.org/W2163719598","https://openalex.org/W2107680156","https://openalex.org/W2387018512","https://openalex.org/W4301184752","https://openalex.org/W1509797384","https://openalex.org/W2035833967","https://openalex.org/W1201576901","https://openalex.org/W2751422192","https://openalex.org/W2479386627"],"abstract_inverted_index":{"Multi-modal":[0,67],"cues,":[1],"including":[2],"spatial":[3],"information,":[4],"facial":[5],"expression":[6],"and":[7,15,41,84,97,123,139],"voiceprint,":[8],"are":[9,141],"introduced":[10],"to":[11,19,24,48,75],"the":[12,29,60,90,94,98,104,130,133],"speech":[13],"separation":[14],"speaker":[16],"extraction":[17],"tasks":[18],"serve":[20],"as":[21],"complementary":[22],"information":[23],"achieve":[25],"better":[26,114],"performance.":[27],"However,":[28],"introduction":[30],"of":[31,39,121,132,135],"these":[32,50],"cues":[33],"brings":[34],"about":[35],"an":[36],"increasing":[37],"number":[38,120],"parameters":[40,122],"model":[42,125],"complexity,":[43],"which":[44,79],"makes":[45],"it":[46],"harder":[47],"deploy":[49],"models":[51],"on":[52,103,111],"resource-constrained":[53],"devices.":[54],"In":[55],"this":[56],"paper,":[57],"we":[58],"alleviate":[59],"aforementioned":[61],"problem":[62],"by":[63],"proposing":[64],"a":[65,117],"Lightweight":[66],"framework":[68],"for":[69],"Speaker":[70],"Extraction":[71],"(LiMuSE).":[72],"We":[73,127],"propose":[74],"use":[76],"GC-equipped":[77],"TCN,":[78],"incorporates":[80],"Group":[81],"Communication":[82],"(GC)":[83],"Temporal":[85],"Convolutional":[86],"Network":[87],"(TCN)":[88],"in":[89],"Context":[91],"Codec":[92],"module,":[93],"audio":[95],"block":[96],"fusion":[99],"block.":[100],"The":[101],"experiments":[102],"MC_GRID":[105],"dataset":[106,140],"demonstrate":[107],"that":[108],"LiMuSE":[109],"achieves":[110],"par":[112],"or":[113],"performance":[115],"with":[116],"much":[118],"smaller":[119],"less":[124],"complexity.":[126],"further":[128],"investigate":[129],"impacts":[131],"quantization":[134],"LiMuSE.":[136],"Our":[137],"code":[138],"provided11https://github.com/aispeech-lab/LiMuSE.":[142]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
