{"id":"https://openalex.org/W7166815603","doi":"https://doi.org/10.18653/v1/2026.acl-long.131","title":"RealTalk-CN: A Realistic Chinese Speech Task-Oriented Dialogue Benchmark with Cross-Modal Analysis","display_name":"RealTalk-CN: A Realistic Chinese Speech Task-Oriented Dialogue Benchmark with Cross-Modal Analysis","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166815603","doi":"https://doi.org/10.18653/v1/2026.acl-long.131"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.131","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.131","pdf_url":"https://aclanthology.org/2026.acl-long.131.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.131.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085926780","display_name":"Enzhi Wang","orcid":"https://orcid.org/0000-0003-0309-0251"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Enzhi Wang","raw_affiliation_strings":["TMCC , College of Computer Science , Nankai University RealTalk-CN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TMCC , College of Computer Science , Nankai University RealTalk-CN","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139751239","display_name":"Jiaming Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaming Zhou","raw_affiliation_strings":["TMCC , College of Computer Science , Nankai University RealTalk-CN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TMCC , College of Computer Science , Nankai University RealTalk-CN","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139843692","display_name":"Yuhang Jia","orcid":null},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhang Jia","raw_affiliation_strings":["TMCC , College of Computer Science , Nankai University RealTalk-CN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TMCC , College of Computer Science , Nankai University RealTalk-CN","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113361563","display_name":"Aobo Kong","orcid":null},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Aobo Kong","raw_affiliation_strings":["TMCC , College of Computer Science , Nankai University RealTalk-CN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TMCC , College of Computer Science , Nankai University RealTalk-CN","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067376482","display_name":"Qicheng Li","orcid":null},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qicheng Li","raw_affiliation_strings":["TMCC , College of Computer Science , Nankai University RealTalk-CN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TMCC , College of Computer Science , Nankai University RealTalk-CN","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5139723216","display_name":"Yong Qin","orcid":null},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Qin","raw_affiliation_strings":["TMCC , College of Computer Science , Nankai University RealTalk-CN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TMCC , College of Computer Science , Nankai University RealTalk-CN","institution_ids":["https://openalex.org/I205237279"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I205237279"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.80524524,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2880","last_page":"2897"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9387999773025513,"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":0.9387999773025513,"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/T10465","display_name":"Neurobiology of Language and Bilingualism","score":0.01209999993443489,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.00800000037997961,"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/benchmark","display_name":"Benchmark (surveying)","score":0.4171999990940094},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3305000066757202},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.2522999942302704},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.24549999833106995}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6585000157356262},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4851999878883362},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4805999994277954},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4171999990940094},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37209999561309814},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3305000066757202},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.29089999198913574},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.2522999942302704},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.24549999833106995},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.24199999868869781}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.131","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.131","pdf_url":"https://aclanthology.org/2026.acl-long.131.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.131","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.131","pdf_url":"https://aclanthology.org/2026.acl-long.131.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166815603.pdf","grobid_xml":"https://content.openalex.org/works/W7166815603.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,16,26,179],"speech":[3,47,77],"large":[4],"language":[5],"models":[6,59,158],"(e.g.,":[7],"have":[8],"enabled":[9],"end-to-end":[10],"spoken":[11],"interactions,":[12],"yet":[13],"their":[14],"robustness":[15,146],"realworld":[17],"applications":[18],"remains":[19],"unclear,":[20],"where":[21],"systems":[22],"must":[23],"assist":[24],"users":[25,63],"completing":[27],"specific":[28],"tasks":[29],"under":[30],"complex":[31],"conditions":[32],"such":[33,65],"as":[34,41,43,169],"multiturn,":[35],"ambiguous,":[36],"and":[37,48,74,83,88,124,140,153,165,175,183],"often":[38,84],"spontaneous":[39,86],"speech,":[40],"well":[42],"natural":[44],"alternation":[45],"between":[46],"text.Task-oriented":[49],"dialogue":[50,120],"(TOD)":[51],"offers":[52],"a":[53,132,141,170],"realistic":[54],"scenario":[55],"to":[56,81,147,150,189],"evaluate":[57],"whether":[58],"can":[60],"effectively":[61],"help":[62],"accomplish":[64],"task-oriented":[66],"goals,":[67],"but":[68],"existing":[69],"benchmarks":[70],"are":[71,79,186],"mainly":[72],"text-based,":[73],"the":[75,97,160],"few":[76],"datasets":[78],"limited":[80],"English":[82],"neglect":[85],"disfluencies":[87],"speaker":[89,125,151],"diversity.To":[90],"address":[91],"this":[92,128],"gap,":[93],"we":[94,130],"introduce":[95],"RealTalk-CN,":[96],"first":[98],"Chinese":[99],"multi-turn,":[100],"multi-domain":[101],"speech-text":[102,138],"TOD":[103],"dataset,":[104,129],"containing":[105],"5.4k":[106],"dialogues":[107],"(60K":[108],"turns,":[109],"~150":[110],"hours)":[111],"of":[112],"real":[113],"human-to-human":[114],"recordings":[115],"with":[116],"detailed":[117],"annotations":[118],"for":[119,172],"states,":[121],"disfluency":[122],"types,":[123],"characteristics.Based":[126],"on":[127,156],"propose":[131],"cross-modal":[133],"interaction":[134],"task":[135],"supporting":[136],"dynamic":[137],"switching":[139],"comprehensive":[142],"evaluation":[143,184],"protocol":[144],"assessing":[145],"disfluencies,":[148],"sensitivity":[149],"variation,":[152],"cross-domain":[154],"generalization.Experiments":[155],"state-of-the-art":[157],"demonstrate":[159],"challenges":[161],"posed":[162],"by":[163],"RealTalk-CN":[164],"establish":[166],"its":[167],"value":[168],"benchmark":[171],"developing":[173],"reliable":[174],"fair":[176],"Speech":[177],"LLMs":[178],"real-world":[180],"deployments.The":[181],"dataset":[182],"framework":[185],"available":[187],"1":[188],"encourage":[190],"further":[191],"research.":[192]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}