{"id":"https://openalex.org/W4416034301","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.933","title":"URO-Bench: Towards Comprehensive Evaluation for End-to-End Spoken Dialogue Models","display_name":"URO-Bench: Towards Comprehensive Evaluation for End-to-End Spoken Dialogue Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034301","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.933"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.933","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.933","pdf_url":"https://aclanthology.org/2025.findings-emnlp.933.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.933.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Ruiqi Yan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruiqi Yan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104326367","display_name":"Xiquan Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiquan Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034677845","display_name":"Wenxi Chen","orcid":"https://orcid.org/0009-0005-8303-930X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenxi Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109531461","display_name":"Zhikang Niu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhikang Niu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062835441","display_name":"Chen Yang","orcid":"https://orcid.org/0000-0002-7759-1713"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101838736","display_name":"Ziyang Ma","orcid":"https://orcid.org/0000-0002-8195-3262"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ziyang Ma","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088188138","display_name":"Kai Yu","orcid":"https://orcid.org/0000-0001-6300-0882"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kai Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101293966","display_name":"Xie Chen","orcid":"https://orcid.org/0000-0001-7423-617X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.2763,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.95691002,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"17211","last_page":"17242"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.8054999709129333,"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/T12031","display_name":"Speech and dialogue systems","score":0.8054999709129333,"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/T10028","display_name":"Topic Modeling","score":0.1264999955892563,"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/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.006000000052154064,"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/feature","display_name":"Feature (linguistics)","score":0.29829999804496765},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.2833000123500824},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.27469998598098755},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.2574999928474426},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.24390000104904175}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5637000203132629},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.453000009059906},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4059000015258789},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3831999897956848},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.29829999804496765},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.27469998598098755},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.2574999928474426},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.24390000104904175},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2433999925851822}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.933","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.933","pdf_url":"https://aclanthology.org/2025.findings-emnlp.933.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.933","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.933","pdf_url":"https://aclanthology.org/2025.findings-emnlp.933.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3278014984","display_name":null,"funder_award_id":"U23B2018","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8721642152","display_name":null,"funder_award_id":"2021SHZDZX0102","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034301.pdf","grobid_xml":"https://content.openalex.org/works/W4416034301.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,11,53,106,124,134,146,163,190],"large":[3],"language":[4],"models":[5,15,176,184],"(LLMs)":[6],"have":[7],"driven":[8],"significant":[9],"progress":[10,189],"endto-end":[12],"spoken":[13,102,174],"dialogue":[14,103,175],"(SDMs).In":[16],"contrast":[17],"to":[18,187],"text-based":[19],"LLMs,":[20],"the":[21,70,101,158,171],"evaluation":[22,181],"framework":[23],"for":[24,51,66,160],"SDMs":[25,52,120],"should":[26],"encompass":[27],"both":[28],"cognitive":[29],"dimensions":[30],"(e.g.,":[31,38],"logical":[32],"reasoning,":[33],"knowledge)":[34],"and":[35,81,92,109,139,152,185],"speech-related":[36],"aspects":[37],"paralinguistic":[39,150],"cues,":[40],"audio":[41,153],"quality).However,":[42],"there":[43],"is":[44,69,84],"still":[45],"a":[46,179],"lack":[47],"of":[48,136,149,173,182],"comprehensive":[49],"evaluations":[50,76,148],"speech-to-speech":[54],"(S2S)":[55],"scenarios.To":[56],"address":[57],"this":[58,164,191],"gap,":[59],"we":[60],"propose":[61],"URO-Bench,":[62],"an":[63],"extensive":[64],"benchmark":[65,73,83,115],"SDMs.Notably,":[67],"URO-Bench":[68,168],"first":[71],"S2S":[72],"that":[74,117,167],"covers":[75],"about":[77],"multilingualism,":[78],"multi-round":[79],"dialogues,":[80],"paralinguistics.Our":[82],"divided":[85],"into":[86],"two":[87],"difficulty":[88],"levels:":[89],"basic":[90],"track":[91,188],"pro":[93],"track,":[94],"each":[95],"comprising":[96],"20":[97],"test":[98],"sets,":[99],"evaluating":[100],"model's":[104],"abilities":[105],"Understanding,":[107],"Reasoning,":[108],"Oral":[110],"conversation.Evaluations":[111],"on":[112],"our":[113],"proposed":[114],"reveal":[116],"current":[118],"opensource":[119],"perform":[121],"rather":[122],"well":[123],"daily":[125],"QA":[126],"tasks,":[127],"but":[128],"lag":[129],"behind":[130],"their":[131],"backbone":[132],"LLMs":[133],"terms":[135],"instruction-following":[137],"ability":[138],"also":[140],"suffer":[141],"from":[142],"catastrophic":[143],"forgetting.Their":[144],"performance":[145],"advanced":[147],"information":[151],"understanding":[154],"remains":[155],"subpar,":[156],"highlighting":[157],"need":[159],"further":[161],"research":[162],"direction.We":[165],"hope":[166],"can":[169],"facilitate":[170],"development":[172],"by":[177],"providing":[178],"multifaceted":[180],"existing":[183],"helping":[186],"area.":[192]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-08T00:00:00"}