{"id":"https://openalex.org/W7224918592","doi":"https://doi.org/10.48550/arxiv.2610.39828","title":"SpeakerTurn: Target-Speaker Semantic Turn Detection in Multi-Speaker Environments","display_name":"SpeakerTurn: Target-Speaker Semantic Turn Detection in Multi-Speaker Environments","publication_year":2026,"publication_date":"2026-10-29","ids":{"openalex":"https://openalex.org/W7224918592","doi":"https://doi.org/10.48550/arxiv.2610.39828"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.39828","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.39828","pdf_url":"https://arxiv.org/pdf/2610.39828","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.39828","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160167216","display_name":"Nan Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I15062923","display_name":"Tianjin Normal University","ror":"https://ror.org/05x2td559","country_code":"CN","type":"education","lineage":["https://openalex.org/I15062923"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Nan","raw_affiliation_strings":["School of Computer and Information Engineering , Tianjin Normal University , Tianjin , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer and Information Engineering , Tianjin Normal University , Tianjin , China","institution_ids":["https://openalex.org/I15062923"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160153229","display_name":"Hetao Shan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I15062923","display_name":"Tianjin Normal University","ror":"https://ror.org/05x2td559","country_code":"CN","type":"education","lineage":["https://openalex.org/I15062923"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shan, Hetao","raw_affiliation_strings":["School of Computer and Information Engineering , Tianjin Normal University , Tianjin , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer and Information Engineering , Tianjin Normal University , Tianjin , China","institution_ids":["https://openalex.org/I15062923"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160160821","display_name":"Jintao Liang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang, Jintao","raw_affiliation_strings":["School of Artificial Intelligence , Tianjin University , Tianjin , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence , Tianjin University , Tianjin , China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160194518","display_name":"Jiahao Yan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan, Jiahao","raw_affiliation_strings":["School of Artificial Intelligence , Tianjin University , Tianjin , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence , Tianjin University , Tianjin , China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160228009","display_name":"Longbiao Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Longbiao","raw_affiliation_strings":["School of Artificial Intelligence , Tianjin University , Tianjin , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence , Tianjin University , Tianjin , China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090455974","display_name":"\u9ec4\u56fe\u658c Huang Tubin","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Tubin","raw_affiliation_strings":["Shanghai Shenqijiyuan Intelligent Terminal Co. , Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Shenqijiyuan Intelligent Terminal Co. , Ltd","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5160200089","display_name":"Min Xu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Min","raw_affiliation_strings":["Shanghai Shenqijiyuan Intelligent Terminal Co. , Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Shenqijiyuan Intelligent Terminal Co. , Ltd","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9911999702453613,"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":0.9911999702453613,"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":0.007199999876320362,"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":0.0010000000474974513,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/turn-detection","display_name":"turn detection","score":0.7129999995231628},{"id":"https://openalex.org/keywords/multi-speaker-speech-recognition","display_name":"multi-speaker speech recognition","score":0.7820000052452087},{"id":"https://openalex.org/keywords/speech-language-models","display_name":"speech language models","score":0.3970000147819519}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.781000018119812},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7418000102043152},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.6606000065803528},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5667999982833862},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5400999784469604},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4986000061035156},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4648999869823456},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.39410001039505005},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.3614000082015991},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.3294000029563904},{"id":"https://openalex.org/C17231256","wikidata":"https://www.wikidata.org/wiki/Q5156540","display_name":"Completeness (order theory)","level":2,"score":0.3206999897956848},{"id":"https://openalex.org/C166955791","wikidata":"https://www.wikidata.org/wiki/Q629579","display_name":"Macro","level":2,"score":0.3107999861240387},{"id":"https://openalex.org/C59656382","wikidata":"https://www.wikidata.org/wiki/Q191536","display_name":"Conjunction (astronomy)","level":2,"score":0.2809999883174896},{"id":"https://openalex.org/C67277372","wikidata":"https://www.wikidata.org/wiki/Q7449085","display_name":"Semantic role labeling","level":3,"score":0.27869999408721924},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.26510000228881836},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.25920000672340393},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2590999901294708},{"id":"https://openalex.org/C2984865316","wikidata":"https://www.wikidata.org/wiki/Q25481968","display_name":"Speech act","level":2,"score":0.2531000077724457}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.39828","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.39828","pdf_url":"https://arxiv.org/pdf/2610.39828","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.39828","doi":"https://doi.org/10.48550/arxiv.2610.39828","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.39828","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.39828","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.39828","pdf_url":"https://arxiv.org/pdf/2610.39828","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7224918592.pdf","grobid_xml":"https://content.openalex.org/works/W7224918592.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7151004253","https://openalex.org/W4388276260","https://openalex.org/W2803914087","https://openalex.org/W7138328030","https://openalex.org/W1550575505","https://openalex.org/W4297841778","https://openalex.org/W4402111449","https://openalex.org/W2098765248","https://openalex.org/W4385823037","https://openalex.org/W65840850"],"abstract_inverted_index":{"Semantic":[0],"completeness":[1],"alone":[2],"cannot":[3],"determine":[4],"when":[5,173],"an":[6,20,63],"assistant":[7],"should":[8],"respond":[9],"in":[10],"a":[11,14,47,59,91,113],"multi-speaker":[12,115],"environment:":[13],"completed":[15],"utterance":[16],"may":[17],"belong":[18],"to":[19,74],"interfering":[21],"speaker,":[22],"while":[23],"the":[24,52,75],"designated":[25],"user":[26],"is":[27],"still":[28],"speaking,":[29],"acknowledging,":[30],"or":[31],"requesting":[32],"time.":[33],"We":[34,44,95],"therefore":[35],"study":[36],"semantic":[37,72,110,164],"turn":[38,56,155,165],"inference":[39],"conditioned":[40],"on":[41,68],"speaker":[42,107],"identity.":[43],"propose":[45],"SpeakerTurn,":[46],"framework":[48],"that":[49],"jointly":[50],"predicts":[51],"target":[53,77,162],"transcript":[54],"and":[55,62,87,109,125,142,148,167],"state":[57],"from":[58],"speech":[60,175],"mixture":[61],"independent":[64],"target-speaker":[65],"reference.":[66],"Built":[67],"CocktailASR-1,":[69],"it":[70],"links":[71],"decisions":[73,104],"corresponding":[76],"content":[78],"through":[79],"joint":[80],"supervision,":[81],"distinguishing":[82],"complete,":[83],"incomplete,":[84],"backchannel,":[85],"wait,":[86],"target-absent":[88],"states,":[89],"with":[90],"separate":[92,171],"interruption":[93,138],"task.":[94],"also":[96],"examine":[97],"whether":[98],"structured":[99],"chain-of-thought":[100],"(CoT)":[101],"supervision":[102],"improves":[103,150],"by":[105],"representing":[106],"presence":[108],"cues.":[111],"On":[112],"synthetic":[114],"test":[116],"set,":[117],"SpeakerTurn":[118],"achieves":[119],"five-state":[120],"macro":[121,156],"F1":[122],"of":[123,131],"0.811":[124],"target-transcription":[126],"character":[127],"error":[128],"rate":[129],"(CER)":[130],"4.20%,":[132],"correctly":[133],"resolving":[134],"all":[135],"ten":[136],"reference-swapped":[137],"pairs.":[139],"Joint-format":[140],"transcription":[141,152],"native-interface":[143],"recognition":[144,168],"nevertheless":[145],"behave":[146],"differently,":[147],"CoT":[149],"validation":[151],"without":[153],"improving":[154],"F1.":[157],"These":[158],"results":[159],"show":[160],"why":[161],"attribution,":[163],"discrimination,":[166],"retention":[169],"require":[170],"assessment":[172],"adapting":[174],"language":[176],"models":[177],"for":[178],"speaker-conditioned":[179],"interaction.":[180]},"counts_by_year":[],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2026-10-31T00:00:00"}