{"id":"https://openalex.org/W4406461781","doi":"https://doi.org/10.1109/slt61566.2024.10832300","title":"Just ASR + LLM? A Study on Speech Large Language Models\u2019 Ability to Identify And Understand Speaker in Spoken Dialogue","display_name":"Just ASR + LLM? A Study on Speech Large Language Models\u2019 Ability to Identify And Understand Speaker in Spoken Dialogue","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461781","doi":"https://doi.org/10.1109/slt61566.2024.10832300"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832300","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832300","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","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/A5101600013","display_name":"Junkai Wu","orcid":"https://orcid.org/0000-0003-1541-0267"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junkai Wu","raw_affiliation_strings":["University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086248084","display_name":"Xulin Fan","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xulin Fan","raw_affiliation_strings":["University of Illinois-Urbana Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois-Urbana Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074851450","display_name":"Bo-Ru Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bo-Ru Lu","raw_affiliation_strings":["University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109460203","display_name":"Xilin Jiang","orcid":"https://orcid.org/0009-0000-9373-0851"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xilin Jiang","raw_affiliation_strings":["Columbia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033351155","display_name":"Nima Mesgarani","orcid":"https://orcid.org/0000-0002-2987-759X"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nima Mesgarani","raw_affiliation_strings":["Columbia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004778663","display_name":"Mark Hasegawa\u2010Johnson","orcid":"https://orcid.org/0000-0002-5631-2893"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Hasegawa-Johnson","raw_affiliation_strings":["University of Illinois-Urbana Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois-Urbana Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087215613","display_name":"Mari Ostendorf","orcid":null},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mari Ostendorf","raw_affiliation_strings":["University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3055,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.6847719,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1137","last_page":"1143"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9986000061035156,"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":0.9986000061035156,"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/T12031","display_name":"Speech and dialogue systems","score":0.998199999332428,"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":0.9822999835014343,"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":0.7586100101470947},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.6607002019882202},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6226836442947388},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43191292881965637},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.36488938331604004},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32452112436294556}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7586100101470947},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.6607002019882202},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6226836442947388},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43191292881965637},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.36488938331604004},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32452112436294556},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832300","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832300","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5400000214576721}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2800448574","https://openalex.org/W2972359262","https://openalex.org/W2998572311","https://openalex.org/W3168867926","https://openalex.org/W3209984917","https://openalex.org/W4311000453","https://openalex.org/W4322718191","https://openalex.org/W4365601444","https://openalex.org/W4377130946","https://openalex.org/W4380714711","https://openalex.org/W4384918448","https://openalex.org/W4388718054","https://openalex.org/W4391021627","https://openalex.org/W4399912676","https://openalex.org/W4400104114","https://openalex.org/W4404781855","https://openalex.org/W4405552797","https://openalex.org/W6772349387","https://openalex.org/W6796581206","https://openalex.org/W6847363464","https://openalex.org/W6850625674","https://openalex.org/W6853249747","https://openalex.org/W6853937136","https://openalex.org/W6854866820","https://openalex.org/W6856800273","https://openalex.org/W6857054612","https://openalex.org/W6859099255","https://openalex.org/W6869365648","https://openalex.org/W6870283767"],"related_works":["https://openalex.org/W3188962172","https://openalex.org/W2772917594","https://openalex.org/W4312825515","https://openalex.org/W4306742369","https://openalex.org/W2388125677","https://openalex.org/W4303457083","https://openalex.org/W2131146434","https://openalex.org/W2951359407","https://openalex.org/W3204019825","https://openalex.org/W633922780"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"we":[3,68],"have":[4,23],"observed":[5],"a":[6,60,110,174],"rapid":[7],"advancement":[8],"in":[9,31,44,59,114,119,181],"speech":[10],"language":[11],"models":[12,94],"(SpeechLLMs),":[13],"catching":[14],"up":[15],"with":[16,128],"humans\u2019":[17],"listening":[18,37],"and":[19,54,88,96,101,134,151],"reasoning":[20,157],"abilities.":[21],"SpeechLLMs":[22,143,180],"demonstrated":[24],"impressive":[25],"spoken":[26,52],"dialog":[27],"question-answering":[28],"(SQA)":[29],"performance":[30],"benchmarks":[32],"like":[33],"Gaokao,":[34],"the":[35,40,51,70,80,141,149,159],"English":[36],"test":[38],"of":[39,57,92,179],"college":[41],"entrance":[42],"exam":[43],"China,":[45],"which":[46,122],"seemingly":[47],"requires":[48],"understanding":[49],"both":[50,99],"content":[53],"voice":[55],"characteristics":[56],"speakers":[58],"conversation.":[61],"However,":[62],"after":[63],"carefully":[64],"examining":[65],"Gaokao\u2019s":[66],"questions,":[67,121],"find":[69],"correct":[71,129],"answers":[72],"to":[73,154],"many":[74],"questions":[75,117,171],"can":[76,123],"be":[77,125],"inferred":[78],"from":[79,148,158],"conversation":[81,160],"transcript":[82],"alone,":[83],"i.e.":[84],"without":[85,162],"speaker":[86,130,146],"segmentation":[87],"identification.":[89,131],"Our":[90],"evaluation":[91,177],"state-of-the-art":[93],"Qwen-Audio":[95],"WavLLM":[97],"on":[98,169],"Gaokao":[100],"our":[102],"proposed":[103],"\u201cWhat":[104],"Do":[105],"You":[106],"Like?\u201d":[107],"dataset":[108],"shows":[109],"significantly":[111],"higher":[112],"accuracy":[113],"these":[115],"context-based":[116],"than":[118],"identity-critical":[120,170],"only":[124],"answered":[126],"reliably":[127],"The":[132],"results":[133],"analysis":[135],"suggest":[136],"that":[137,166],"when":[138],"solving":[139],"SQA,":[140],"current":[142],"exhibit":[144],"limited":[145],"awareness":[147],"audio":[150],"behave":[152],"similarly":[153],"an":[155],"LLM":[156],"transcription":[161],"sound.":[163],"We":[164],"propose":[165],"tasks":[167],"focused":[168],"could":[172],"offer":[173],"more":[175],"accurate":[176],"framework":[178],"SQA.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}