{"id":"https://openalex.org/W7148456556","doi":"https://doi.org/10.1109/asru65441.2025.11434620","title":"LauraTSE: Target Speaker Extraction using Auto-Regressive Decoder-Only Language Models","display_name":"LauraTSE: Target Speaker Extraction using Auto-Regressive Decoder-Only Language Models","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148456556","doi":"https://doi.org/10.1109/asru65441.2025.11434620"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434620","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434620","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5132821426","display_name":"Beilong Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Beilong Tang","raw_affiliation_strings":["Duke Kunshan University,Kunshan,China"],"affiliations":[{"raw_affiliation_string":"Duke Kunshan University,Kunshan,China","institution_ids":["https://openalex.org/I4210159968"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024016041","display_name":"Bang Zeng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bang Zeng","raw_affiliation_strings":["Duke Kunshan University,Kunshan,China"],"affiliations":[{"raw_affiliation_string":"Duke Kunshan University,Kunshan,China","institution_ids":["https://openalex.org/I4210159968"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111078324","display_name":"Moran Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Li","raw_affiliation_strings":["Duke Kunshan University,Kunshan,China"],"affiliations":[{"raw_affiliation_string":"Duke Kunshan University,Kunshan,China","institution_ids":["https://openalex.org/I4210159968"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5132821426"],"corresponding_institution_ids":["https://openalex.org/I4210159968"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87566762,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8327999711036682,"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":0.8327999711036682,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.05860000103712082,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.013299999758601189,"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/speaker-recognition","display_name":"Speaker recognition","score":0.36410000920295715},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3467000126838684},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.31470000743865967},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.28130000829696655},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.271699994802475},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2662000060081482}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6703000068664551},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5415999889373779},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47519999742507935},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4104999899864197},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.36410000920295715},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3467000126838684},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.31470000743865967},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.28130000829696655},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.271699994802475},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.25949999690055847},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2538999915122986},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.25380000472068787}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434620","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434620","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1552314771","https://openalex.org/W2067295501","https://openalex.org/W2952218014","https://openalex.org/W2972436155","https://openalex.org/W2981087920","https://openalex.org/W3097653961","https://openalex.org/W3097777922","https://openalex.org/W3131332223","https://openalex.org/W3151596526","https://openalex.org/W3163652268","https://openalex.org/W3174264304","https://openalex.org/W3196475561","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4221144097","https://openalex.org/W4225302959","https://openalex.org/W4367597591","https://openalex.org/W4372340947","https://openalex.org/W4385822255","https://openalex.org/W4385822449","https://openalex.org/W4385822827","https://openalex.org/W4392825061","https://openalex.org/W4392903389","https://openalex.org/W4392909571","https://openalex.org/W4400111385","https://openalex.org/W4402111497","https://openalex.org/W4402111636","https://openalex.org/W4402111955","https://openalex.org/W4402112342","https://openalex.org/W4402112399","https://openalex.org/W4410639153","https://openalex.org/W4412719241","https://openalex.org/W4412945293","https://openalex.org/W7117961032"],"related_works":[],"abstract_inverted_index":{"We":[0],"propose":[1],"LauraTSE,":[2],"an":[3],"Auto-Regressive":[4],"Decoder-Only":[5],"Language":[6],"Model":[7],"for":[8],"Target":[9],"Speaker":[10],"Extraction":[11],"built":[12],"upon":[13],"the":[14,27,31,38,43,63,72,75,98,102,105],"LauraGPT":[15],"backbone.":[16],"LauraTSE":[17],"employs":[18],"a":[19,57],"small-scale":[20],"auto-regressive":[21],"decoder-only":[22],"language":[23,60],"model":[24,61],"that":[25,84],"generates":[26],"initial":[28],"layers":[29],"of":[30,41,104],"target":[32],"speech\u2019s":[33],"discrete":[34],"codec":[35,65],"representations":[36],"from":[37,70],"continuous":[39],"embeddings":[40],"both":[42,71],"mixture":[44,73],"and":[45,74,101],"reference":[46,76],"speech.":[47],"These":[48],"outputs":[49],"serve":[50],"as":[51],"coarsegrained":[52],"predictions.":[53],"To":[54],"refine":[55],"them,":[56],"one-step":[58],"encoder-only":[59,106],"reconstructs":[62],"full":[64],"representation":[66],"by":[67],"integrating":[68],"information":[69],"speech,":[77],"adding":[78],"fine-grained":[79],"details.":[80],"Experimental":[81],"results":[82],"show":[83],"our":[85],"approach":[86],"can":[87],"achieve":[88],"promising":[89],"performance.":[90],"Additionally,":[91],"we":[92],"conduct":[93],"ablation":[94],"studies":[95],"to":[96],"investigate":[97],"data":[99],"scalability":[100],"contribution":[103],"model.":[107]},"counts_by_year":[],"updated_date":"2026-04-03T16:44:17.987007","created_date":"2026-04-03T00:00:00"}