{"id":"https://openalex.org/W7166827216","doi":"https://doi.org/10.18653/v1/2026.findings-acl.263","title":"MTR-DuplexBench: Towards a Comprehensive Evaluation of Multi-Round Conversations for Full-Duplex Speech Language Models","display_name":"MTR-DuplexBench: Towards a Comprehensive Evaluation of Multi-Round Conversations for Full-Duplex Speech Language Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166827216","doi":"https://doi.org/10.18653/v1/2026.findings-acl.263"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.263","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.263","pdf_url":"https://aclanthology.org/2026.findings-acl.263.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: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.263.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139779938","display_name":"He Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang He","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139831080","display_name":"Wenqian Cui","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenqian Cui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063907750","display_name":"Haoning Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haoning Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139747052","display_name":"Xiao-Hui Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiao-Hui Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139825030","display_name":"Lei Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei Zhu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139850880","display_name":"Haoli Bai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haoli Bai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139736017","display_name":"Ma Shaohua","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma Shaohua","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139751926","display_name":"Irwin King","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Irwin King","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.81689541,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5334","last_page":"5351"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.5715000033378601,"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":0.5715000033378601,"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/T10860","display_name":"Speech and Audio Processing","score":0.07199999690055847,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.06530000269412994,"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/conversation","display_name":"Conversation","score":0.35510000586509705},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.34139999747276306},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3337000012397766},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.29679998755455017},{"id":"https://openalex.org/keywords/language-identification","display_name":"Language identification","score":0.2808000147342682}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6033999919891357},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4602000117301941},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42320001125335693},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.35510000586509705},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.34139999747276306},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3361999988555908},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3337000012397766},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3212999999523163},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.29679998755455017},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.2808000147342682},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2799000144004822},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.25189998745918274}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.263","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.263","pdf_url":"https://aclanthology.org/2026.findings-acl.263.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: ACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.263","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.263","pdf_url":"https://aclanthology.org/2026.findings-acl.263.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: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7220960259437561}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322942","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166827216.pdf","grobid_xml":"https://content.openalex.org/works/W7166827216.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Full-Duplex":[0],"Speech":[1],"Language":[2],"Models":[3],"(FD-SLMs)":[4],"enable":[5],"real-time,":[6],"overlapping":[7],"conversational":[8,61,103],"interactions,":[9,28],"offering":[10],"a":[11,73,78],"more":[12],"dynamic":[13],"user":[14],"experience":[15],"compared":[16],"to":[17],"traditional":[18],"halfduplex":[19],"models.However,":[20],"existing":[21,54],"benchmarks":[22,55],"primarily":[23],"focus":[24,57],"on":[25,59],"evaluating":[26,60],"single-round":[27],"neglecting":[29,63],"the":[30,129],"complexities":[31],"of":[32,82,133],"multiround":[33],"communication.Evaluating":[34],"FD-SLMs":[35,115],"in":[36,46,118],"multi-round":[37,80],"settings":[38],"poses":[39],"significant":[40],"challenges,":[41],"including":[42,102],"blurred":[43],"turn":[44],"boundaries":[45],"communication":[47],"and":[48,109,125,131],"context":[49],"inconsistency":[50],"during":[51],"model":[52],"inference.Also,":[53],"often":[56],"solely":[58],"features,":[62,104],"other":[64],"critical":[65],"aspects.To":[66],"address":[67],"these":[68],"gaps,":[69],"we":[70],"introduce":[71],"MTR-DuplexBench,":[72],"novel":[74],"benchmark":[75],"designed":[76],"for":[77,93],"comprehensive":[79],"evaluation":[81,100,126],"FD-SLMs.MTR-DuplexBench":[83],"not":[84],"only":[85],"segments":[86],"continuous":[87],"full-duplex":[88],"dialogues":[89],"into":[90],"discrete":[91],"turns":[92],"turn-by-turn":[94],"assessment":[95],"but":[96],"also":[97],"incorporates":[98],"various":[99],"aspects,":[101],"dialogue":[105],"quality,":[106],"instruction":[107],"following,":[108],"safety.Experimental":[110],"results":[111],"reveal":[112],"that":[113],"current":[114],"face":[116],"difficulties":[117],"maintaining":[119],"consistent":[120],"performance":[121],"across":[122],"multiple":[123],"rounds":[124],"dimensions,":[127],"highlighting":[128],"necessity":[130],"effectiveness":[132],"our":[134],"benchmark.":[135]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}