{"id":"https://openalex.org/W4413157351","doi":"https://doi.org/10.1109/tcds.2025.3598687","title":"Typing to Listen at the Cocktail Party: Text-Guided Target Speaker Extraction","display_name":"Typing to Listen at the Cocktail Party: Text-Guided Target Speaker Extraction","publication_year":2025,"publication_date":"2025-08-13","ids":{"openalex":"https://openalex.org/W4413157351","doi":"https://doi.org/10.1109/tcds.2025.3598687"},"language":"en","primary_location":{"id":"doi:10.1109/tcds.2025.3598687","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcds.2025.3598687","pdf_url":null,"source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Cognitive and Developmental Systems","raw_type":"journal-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":null,"display_name":"Xiang Hao","orcid":"https://orcid.org/0009-0005-4364-4556"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xiang Hao","raw_affiliation_strings":["Department of Data Science and Artificial Intelligence, The Hong Kong Polytechnic University, Hung Hom, Hong Kong SAR","Department of Data Science and Artificial Intelligence, The Hong Kong Polytechnic University, Hong Kong SAR"],"raw_orcid":"https://orcid.org/0009-0005-4364-4556","affiliations":[{"raw_affiliation_string":"Department of Data Science and Artificial Intelligence, The Hong Kong Polytechnic University, Hung Hom, Hong Kong SAR","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"Department of Data Science and Artificial Intelligence, The Hong Kong Polytechnic University, Hong Kong SAR","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018341980","display_name":"Jibin Wu","orcid":"https://orcid.org/0000-0003-0135-4188"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jibin Wu","raw_affiliation_strings":["Department of Data Science and Artificial Intelligence, the Department of Computing, and the Research Center of Data Science and Artificial Intelligence, The Hong Kong Polytechnic University, Hung Hom, Hong Kong SAR","Department of Data Science and Artificial Intelligence, The Hong Kong Polytechnic University, Hong Kong SAR"],"raw_orcid":"https://orcid.org/0000-0003-0135-4188","affiliations":[{"raw_affiliation_string":"Department of Data Science and Artificial Intelligence, the Department of Computing, and the Research Center of Data Science and Artificial Intelligence, The Hong Kong Polytechnic University, Hung Hom, Hong Kong SAR","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"Department of Data Science and Artificial Intelligence, The Hong Kong Polytechnic University, Hong Kong SAR","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102286496","display_name":"Jianwei Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianwei Yu","raw_affiliation_strings":["Tencent, Shenzhen, China","Tencent"],"raw_orcid":"https://orcid.org/0000-0002-2449-1436","affiliations":[{"raw_affiliation_string":"Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chenglin Xu","orcid":"https://orcid.org/0000-0002-1584-6282"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenglin Xu","raw_affiliation_strings":["Tencent, Shenzhen, China","Tencent"],"raw_orcid":"https://orcid.org/0000-0002-1584-6282","affiliations":[{"raw_affiliation_string":"Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025285243","display_name":"Kay Chen Tan","orcid":"https://orcid.org/0000-0002-6802-2463"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Kay Chen Tan","raw_affiliation_strings":["Department of Data Science and Artificial Intelligence and the Research Center of Data Science and Artificial Intelligence, The Hong Kong Polytechnic University, Hung Hom, Hong Kong SAR","Department of Data Science and Artificial Intelligence, The Hong Kong Polytechnic University, Hong Kong SAR"],"raw_orcid":"https://orcid.org/0000-0002-6802-2463","affiliations":[{"raw_affiliation_string":"Department of Data Science and Artificial Intelligence and the Research Center of Data Science and Artificial Intelligence, The Hong Kong Polytechnic University, Hung Hom, Hong Kong SAR","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"Department of Data Science and Artificial Intelligence, The Hong Kong Polytechnic University, Hong Kong SAR","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.396,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.85332295,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"18","issue":"2","first_page":"361","last_page":"372"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9488000273704529,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9488000273704529,"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/T13155","display_name":"Digital Communication and Language","score":0.9388999938964844,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9223999977111816,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8615174293518066},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6172064542770386},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5016565322875977},{"id":"https://openalex.org/keywords/typing","display_name":"Typing","score":0.4827396273612976},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36063462495803833}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8615174293518066},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6172064542770386},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5016565322875977},{"id":"https://openalex.org/C2781209916","wikidata":"https://www.wikidata.org/wiki/Q3215756","display_name":"Typing","level":2,"score":0.4827396273612976},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36063462495803833}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcds.2025.3598687","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcds.2025.3598687","pdf_url":null,"source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Cognitive and Developmental Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2159245610","display_name":null,"funder_award_id":"62306259","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3518335283","display_name":null,"funder_award_id":"P0053699","funder_id":"https://openalex.org/F4320322598","funder_display_name":"Hong Kong Polytechnic University"},{"id":"https://openalex.org/G408564432","display_name":null,"funder_award_id":"P0053758","funder_id":"https://openalex.org/F4320322598","funder_display_name":"Hong Kong Polytechnic University"},{"id":"https://openalex.org/G6213110468","display_name":null,"funder_award_id":"P0052694","funder_id":"https://openalex.org/F4320322598","funder_display_name":"Hong Kong Polytechnic University"},{"id":"https://openalex.org/G7668570403","display_name":null,"funder_award_id":"P0043563","funder_id":"https://openalex.org/F4320322598","funder_display_name":"Hong Kong Polytechnic University"},{"id":"https://openalex.org/G8504764422","display_name":null,"funder_award_id":"P0046094","funder_id":"https://openalex.org/F4320322598","funder_display_name":"Hong Kong Polytechnic University"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322598","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W3176169626","https://openalex.org/W2390279801","https://openalex.org/W1606200072","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Humans":[0],"can":[1,106],"easily":[2],"isolate":[3],"a":[4,8,12,27,73,83,138,168,174,196,214],"single":[5],"speaker":[6,35,139],"from":[7,94],"complex":[9],"acoustic":[10],"environment,":[11],"capability":[13],"referred":[14],"to":[15,53,96,131],"as":[16,61,63,109,167],"the":[17,31,54,129,133,162,187,201,207],"\u201cCocktail":[18],"Party":[19],"Effect.\u201d":[20],"However,":[21],"replicating":[22],"this":[23,70,81],"ability":[24],"has":[25],"been":[26],"significant":[28],"challenge":[29],"in":[30,199],"field":[32],"of":[33,58,137,164,190,209],"target":[34],"extraction":[36,134],"(TSE).":[37],"Traditional":[38],"TSE":[39,76,210],"approaches":[40],"predominantly":[41],"rely":[42],"on":[43,120],"voiceprints,":[44],"which":[45],"raise":[46],"privacy":[47,115],"concerns":[48,116],"and":[49,56,117,140,160,205],"face":[50],"issues":[51],"related":[52],"quality":[55],"availability":[57],"enrollment":[59],"samples,":[60],"well":[62],"intra-speaker":[64,144],"variability.":[65],"To":[66],"address":[67],"these":[68],"issues,":[69],"work":[71,185],"introduces":[72],"novel":[74],"text-guided":[75],"paradigm":[77],"named":[78],"LLM-TSE.":[79],"In":[80],"paradigm,":[82],"state-of-the-art":[84,176],"large":[85],"language":[86],"model,":[87],"LLaMA":[88],"2,":[89],"processes":[90],"typed":[91],"text":[92,166],"input":[93],"users":[95],"extract":[97],"semantic":[98],"cues.":[99,183],"We":[100],"demonstrate":[101,161],"that":[102],"textual":[103,149],"descriptions":[104],"alone":[105,159],"effectively":[107],"serve":[108],"cues":[110,158,180],"for":[111],"extraction,":[112],"thus":[113],"addressing":[114],"reducing":[118],"dependency":[119],"voiceprints.":[121],"Furthermore,":[122],"our":[123],"approach":[124],"offers":[125],"flexibility":[126],"by":[127,146,212],"allowing":[128],"user":[130],"specify":[132],"or":[135],"suppression":[136],"enhances":[141],"robustness":[142],"against":[143],"variability":[145],"incorporating":[147],"context-dependent":[148],"information.":[150],"Experimental":[151],"results":[152],"show":[153],"competitive":[154],"performance":[155],"with":[156,181,192],"text-based":[157,179],"effectiveness":[163],"using":[165],"task":[169],"selector.":[170],"Additionally,":[171],"they":[172],"achieve":[173],"new":[175,197],"when":[177],"combining":[178],"pre-registered":[182],"This":[184],"represents":[186],"first":[188],"integration":[189],"LLMs":[191],"TSE,":[193],"potentially":[194],"establishing":[195],"benchmark":[198],"solving":[200],"cocktail":[202],"party":[203],"problem":[204],"expanding":[206],"scope":[208],"applications":[211],"providing":[213],"versatile,":[215],"privacy-conscious":[216],"solution.":[217],"Demo":[218],"is":[219],"provided":[220],"at":[221],"https://github.com/LLM-TSE/llmtse.github.io":[222]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-09T06:08:40.794217","created_date":"2025-10-10T00:00:00"}