{"id":"https://openalex.org/W7164829614","doi":"https://doi.org/10.48550/arxiv.2606.14528","title":"BayLing-Duplex: Native Full-Duplex Speech Dialogue with a Single Autoregressive LLM","display_name":"BayLing-Duplex: Native Full-Duplex Speech Dialogue with a Single Autoregressive LLM","publication_year":2026,"publication_date":"2026-06-12","ids":{"openalex":"https://openalex.org/W7164829614","doi":"https://doi.org/10.48550/arxiv.2606.14528"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.14528","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.14528","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.14528","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078940234","display_name":"Qingkai Fang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fang, Qingkai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045398529","display_name":"Shoutao Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Shoutao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138649406","display_name":"Yang Feng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng, Yang","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":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.49709999561309814,"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":0.49709999561309814,"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/T12128","display_name":"AI in Service Interactions","score":0.2842999994754791,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.0478999987244606,"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/autoregressive-model","display_name":"Autoregressive model","score":0.6448000073432922},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.6115000247955322},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.51910001039505},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4966000020503998},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.43459999561309814},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.40849998593330383},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.34779998660087585}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7318999767303467},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.6448000073432922},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6187000274658203},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6115000247955322},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.51910001039505},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4966000020503998},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.43459999561309814},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4268999993801117},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.40849998593330383},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4075999855995178},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.34779998660087585},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.34299999475479126},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.34220001101493835},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.32839998602867126},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.31520000100135803},{"id":"https://openalex.org/C59656382","wikidata":"https://www.wikidata.org/wiki/Q191536","display_name":"Conjunction (astronomy)","level":2,"score":0.29750001430511475},{"id":"https://openalex.org/C2984865316","wikidata":"https://www.wikidata.org/wiki/Q25481968","display_name":"Speech act","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.25459998846054077},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.14528","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.14528","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.14528","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.14528","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"score":0.6131064295768738,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Real-time,":[0],"full-duplex":[1,79,140],"speech":[2,35],"interaction":[3],"is":[4],"a":[5,77,82,106,146],"key":[6],"feature":[7],"of":[8,61],"next-generation":[9],"spoken":[10],"chatbots,":[11],"allowing":[12],"the":[13,20,59,62,111,132,163],"model":[14],"to":[15,24,57,88,91,95,110,168],"listen":[16],"and":[17,23,32,42,47,93,119,123,136,155,185],"speak":[18],"at":[19],"same":[21],"time":[22],"handle":[25],"natural":[26],"phenomena":[27],"such":[28,39],"as":[29,40],"overlap,":[30],"hesitation,":[31],"barge-in.":[33],"Existing":[34],"language":[36],"models":[37],"(SpeechLMs)":[38],"LLaMA-Omni":[41],"GLM-4-Voice":[43,134],"are":[44],"still":[45],"turn-based":[46,178],"rely":[48],"on":[49,159,180],"an":[50],"external":[51],"Voice":[52],"Activity":[53],"Detection":[54],"(VAD)":[55],"module":[56],"mark":[58],"end":[60],"user's":[63],"turn,":[64],"which":[65],"fundamentally":[66],"limits":[67],"their":[68],"interactive":[69],"ability.":[70],"In":[71],"this":[72],"paper,":[73],"we":[74],"introduce":[75],"BayLing-Duplex,":[76],"native":[78],"SpeechLM":[80],"where":[81],"single":[83],"autoregressive":[84],"LLM":[85],"decides":[86],"when":[87,90,94],"listen,":[89],"speak,":[92],"stop,":[96],"with":[97,126],"no":[98,127],"auxiliary":[99],"turn-taking":[100,153],"module.":[101],"The":[102],"design":[103],"adds":[104],"only":[105,138],"few":[107],"special":[108],"tokens":[109],"standard":[112],"vocabulary,":[113],"so":[114],"it":[115],"transfers":[116],"across":[117],"LLMs":[118],"reuses":[120],"existing":[121],"training":[122],"serving":[124],"stacks":[125],"architectural":[128],"adaptation.":[129],"Starting":[130],"from":[131,166],"public":[133],"checkpoint":[135],"using":[137],"400K":[139],"samples":[141],"for":[142],"fine-tuning":[143],"followed":[144],"by":[145],"lightweight":[147],"DPO":[148],"stage,":[149],"BayLing-Duplex":[150,172],"reaches":[151],"92%":[152],"success":[154,158],"100%":[156],"interruption":[157],"InstructS2S-Eval,":[160],"while":[161],"improving":[162],"speech-response":[164],"score":[165],"2.17":[167],"3.39":[169],"over":[170],"Moshi.":[171],"also":[173],"matches":[174],"or":[175],"surpasses":[176],"its":[177],"counterpart":[179],"Llama":[181],"Questions,":[182,184],"Web":[183],"Alpaca-Eval,":[186],"showing":[187],"that":[188],"simultaneous":[189],"listen-and-speak":[190],"modeling":[191],"does":[192],"not":[193],"sacrifice":[194],"response":[195],"quality.":[196]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-16T00:00:00"}