{"id":"https://openalex.org/W7148752199","doi":"https://doi.org/10.48550/arxiv.2604.01897","title":"FastTurn: Unifying Acoustic and Streaming Semantic Cues for Low-Latency and Robust Turn Detection","display_name":"FastTurn: Unifying Acoustic and Streaming Semantic Cues for Low-Latency and Robust Turn Detection","publication_year":2026,"publication_date":"2026-04-02","ids":{"openalex":"https://openalex.org/W7148752199","doi":"https://doi.org/10.48550/arxiv.2604.01897"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2604.01897","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2604.01897","pdf_url":"https://arxiv.org/pdf/2604.01897","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2604.01897","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125745820","display_name":"Chengyou Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Chengyou","raw_affiliation_strings":["NPU)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NPU)","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125769303","display_name":"Hongfei Xue","orcid":"https://orcid.org/0009-0000-9643-8530","observed_orcids":["https://orcid.org/0009-0000-9643-8530"]},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xue, Hongfei","raw_affiliation_strings":["NPU)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NPU)","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128666324","display_name":"Mingchen Shao","orcid":"https://orcid.org/0009-0005-0732-9233","observed_orcids":["https://orcid.org/0009-0005-0732-9233"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shao, Mingchen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132831075","display_name":"Chunjiang He","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"He, Chunjiang","raw_affiliation_strings":["NPU)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NPU)","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5151150088","display_name":"Jingbin Hu","orcid":"https://orcid.org/0009-0003-8727-2411","observed_orcids":["https://orcid.org/0009-0003-8727-2411"]},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hu, Jingbin","raw_affiliation_strings":["NPU)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NPU)","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125755407","display_name":"Shuiyuan Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Shuiyuan","raw_affiliation_strings":["NPU)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NPU)","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132895180","display_name":"Bo Wu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wu, Bo","raw_affiliation_strings":["NPU)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NPU)","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153470618","display_name":"Yuyu Ji","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ji, Yuyu","raw_affiliation_strings":["NPU)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NPU)","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110274491","display_name":"Jimeng Zheng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng, Jimeng","raw_affiliation_strings":["NPU)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NPU)","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132843306","display_name":"Ruofei Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen, Ruofei","raw_affiliation_strings":["NPU)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NPU)","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5158867251","display_name":"Lei Xie","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xie, Lei","raw_affiliation_strings":["NPU)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NPU)","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":6,"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":0.7666000127792358,"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":0.7666000127792358,"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":0.23080000281333923,"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":0.0020000000949949026,"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":0.9890000224113464},{"id":"https://openalex.org/keywords/acoustic-characteristics","display_name":"acoustic features","score":0.6230000257492065},{"id":"https://openalex.org/keywords/semantic-cues","display_name":"semantic cues","score":0.8119999766349792},{"id":"https://openalex.org/keywords/overlapping-speech","display_name":"overlapping speech","score":0.9290000200271606},{"id":"https://openalex.org/keywords/backchannels","display_name":"backchannels","score":0.7210000157356262},{"id":"https://openalex.org/keywords/noise-robustness","display_name":"noise robustness","score":0.609000027179718},{"id":"https://openalex.org/keywords/spoken-dialogue-systems","display_name":"spoken dialogue systems","score":0.5799999833106995}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8269000053405762},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.746999979019165},{"id":"https://openalex.org/C41661131","wikidata":"https://www.wikidata.org/wiki/Q220764","display_name":"Interrupt","level":3,"score":0.7092000246047974},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.6466000080108643},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5444999933242798},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.49470001459121704},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4916999936103821},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39649999141693115},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3917999863624573},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.335099995136261},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.33399999141693115},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.3107999861240387},{"id":"https://openalex.org/C2776352735","wikidata":"https://www.wikidata.org/wiki/Q2313343","display_name":"Turn-taking","level":3,"score":0.3077999949455261},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.30250000953674316},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29679998755455017},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.2896000146865845},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.2563999891281128},{"id":"https://openalex.org/C2776544517","wikidata":"https://www.wikidata.org/wiki/Q189447","display_name":"Unexpected events","level":2,"score":0.2554999887943268}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2604.01897","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2604.01897","pdf_url":"https://arxiv.org/pdf/2604.01897","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2604.01897","doi":"https://doi.org/10.48550/arxiv.2604.01897","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.01897","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:2604.01897","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2604.01897","pdf_url":"https://arxiv.org/pdf/2604.01897","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","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/W7148752199.pdf","grobid_xml":"https://content.openalex.org/works/W7148752199.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W2889048668","https://openalex.org/W3095410713","https://openalex.org/W3097777922","https://openalex.org/W3198694222","https://openalex.org/W4283067311","https://openalex.org/W4297841547","https://openalex.org/W4400717319","https://openalex.org/W4403556012","https://openalex.org/W4403883071","https://openalex.org/W4404390495","https://openalex.org/W4404990673","https://openalex.org/W4405057125","https://openalex.org/W4405903187","https://openalex.org/W4406093559","https://openalex.org/W4414757003","https://openalex.org/W4414939355","https://openalex.org/W4415433582","https://openalex.org/W6948186523","https://openalex.org/W7148492801"],"related_works":["https://openalex.org/W4415334984","https://openalex.org/W7143447782","https://openalex.org/W7215000145","https://openalex.org/W7204872391","https://openalex.org/W7211871290","https://openalex.org/W4407806352","https://openalex.org/W7134899528","https://openalex.org/W7156565615","https://openalex.org/W7164878316","https://openalex.org/W7202274428"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2],"AudioLLMs":[3],"have":[4],"enabled":[5],"spoken":[6],"dialogue":[7,165],"systems":[8],"to":[9,24],"move":[10],"beyond":[11],"turn-based":[12],"interaction":[13,68],"toward":[14],"real-time":[15],"full-duplex":[16,36,164],"communication,":[17],"where":[18],"the":[19,30,76],"agent":[20],"must":[21],"decide":[22],"when":[23],"speak,":[25],"yield,":[26],"or":[27,48],"interrupt":[28],"while":[29,93,110],"user":[31],"is":[32],"still":[33],"talking.":[34],"Existing":[35],"approaches":[37],"either":[38],"rely":[39],"on":[40,49,121],"voice":[41],"activity":[42],"cues,":[43],"which":[44,52],"lack":[45],"semantic":[46,112],"understanding,":[47],"ASR-based":[50],"modules,":[51],"introduce":[53],"latency":[54,92,148],"and":[55,60,72,86,135,152],"degrade":[56],"under":[57,155],"overlapping":[58,129],"speech":[59],"noise.":[61,137],"Moreover,":[62],"available":[63],"datasets":[64],"rarely":[65],"capture":[66],"realistic":[67],"dynamics,":[69],"limiting":[70],"evaluation":[71],"deployment.":[73],"To":[74,90],"mitigate":[75],"problem,":[77],"we":[78],"propose":[79],"\\textbf{FastTurn},":[80],"a":[81,117],"unified":[82],"framework":[83],"for":[84,162],"low-latency":[85],"robust":[87,154],"turn":[88,127],"detection.":[89],"advance":[91],"maintaining":[94],"performance,":[95],"FastTurn":[96,140],"combines":[97],"streaming":[98],"CTC":[99],"decoding":[100],"with":[101,145],"acoustic":[102,157],"features,":[103],"enabling":[104],"early":[105],"decisions":[106],"from":[107],"partial":[108],"observations":[109],"preserving":[111],"cues.":[113],"We":[114],"also":[115],"release":[116],"test":[118],"set":[119],"based":[120],"real":[122],"human":[123],"dialogue,":[124],"capturing":[125],"authentic":[126],"transitions,":[128],"speech,":[130],"backchannels,":[131],"pauses,":[132],"pitch":[133],"variation,":[134],"environmental":[136],"Experiments":[138],"show":[139],"achieves":[141],"higher":[142],"decision":[143],"accuracy":[144],"lower":[146],"interruption":[147],"than":[149],"representative":[150],"baselines":[151],"remains":[153],"challenging":[156],"conditions,":[158],"demonstrating":[159],"its":[160],"effectiveness":[161],"practical":[163],"systems.":[166]},"counts_by_year":[{"year":2026,"cited_by_count":6}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-04-04T00:00:00"}
