{"id":"https://openalex.org/W7204198224","doi":"https://doi.org/10.48550/arxiv.2608.22101","title":"Beyond Fresh Starts: Stateful Inference for Streaming ASR in Conversational Voice Agents","display_name":"Beyond Fresh Starts: Stateful Inference for Streaming ASR in Conversational Voice Agents","publication_year":2026,"publication_date":"2026-08-22","ids":{"openalex":"https://openalex.org/W7204198224","doi":"https://doi.org/10.48550/arxiv.2608.22101"},"language":null,"primary_location":{"id":"pmh:oai:arXiv.org:2608.22101","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.22101","pdf_url":"https://arxiv.org/pdf/2608.22101","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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/2608.22101","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101227395","display_name":"Sameep Chattopadhyay","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chattopadhyay, Sameep","raw_affiliation_strings":["SRI International"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI International","institution_ids":["https://openalex.org/I1298353152"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056150502","display_name":"Alexander Erdmann","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Erdmann, Alexander","raw_affiliation_strings":["University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087215613","display_name":"Mari Ostendorf E","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ostendorf, Mari","raw_affiliation_strings":["SRI International"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI International","institution_ids":["https://openalex.org/I1298353152"]}]}],"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":0.9883000254631042,"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":0.9883000254631042,"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":0.01140000019222498,"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":0.0003000000142492354,"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/streaming-speech-recognition","display_name":"streaming speech recognition","score":0.8669999837875366},{"id":"https://openalex.org/keywords/state-management","display_name":"state management","score":0.7429999709129333},{"id":"https://openalex.org/keywords/spoken-dialogue-systems","display_name":"spoken dialogue systems","score":0.8820000290870667},{"id":"https://openalex.org/keywords/backchannels","display_name":"backchannels","score":0.9700000286102295},{"id":"https://openalex.org/keywords/memory-limitations","display_name":"memory constraints","score":0.609000027179718},{"id":"https://openalex.org/keywords/latency-constraints","display_name":"delay constraints","score":0.3109999895095825}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7896000146865845},{"id":"https://openalex.org/C22927095","wikidata":"https://www.wikidata.org/wiki/Q1784206","display_name":"Stateful firewall","level":3,"score":0.66839998960495},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.659600019454956},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6420999765396118},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6001999974250793},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5917999744415283},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5313000082969666},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4796000123023987},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4366999864578247},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37450000643730164},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3720000088214874},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.35019999742507935},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.33079999685287476},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.3043999969959259},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.2892000079154968},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.2680000066757202},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2551000118255615},{"id":"https://openalex.org/C2776788033","wikidata":"https://www.wikidata.org/wiki/Q320769","display_name":"Eavesdropping","level":2,"score":0.2526000142097473}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.22101","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.22101","pdf_url":"https://arxiv.org/pdf/2608.22101","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.22101","doi":"https://doi.org/10.48550/arxiv.2608.22101","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.22101","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.22101","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.22101","pdf_url":"https://arxiv.org/pdf/2608.22101","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality education","score":0.5587284564971924}],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320333051","display_name":"Intelligence Advanced Research Projects Activity","ror":"https://ror.org/01v3fsc55"},{"id":"https://openalex.org/F4320333452","display_name":"Interior Business Center","ror":"https://ror.org/04knezf87"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204198224.pdf","grobid_xml":"https://content.openalex.org/works/W7204198224.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Modern":[0],"voice-agent":[1],"systems":[2,29],"rely":[3],"on":[4,85],"streaming":[5,83],"speech":[6],"recognition":[7],"models":[8,84],"that":[9,70],"operate":[10],"under":[11],"stringent":[12],"latency":[13],"constraints.":[14],"This":[15],"study":[16],"shows":[17],"that,":[18],"due":[19],"to":[20,74],"the":[21],"limited":[22],"memory":[23],"constraints":[24],"of":[25,96],"real-time":[26],"processing,":[27],"these":[28],"are":[30],"adversely":[31],"impacted":[32],"by":[33,48],"conversational":[34],"phenomena":[35],"such":[36],"as":[37],"long":[38],"silences":[39],"and":[40,59],"backchannels.":[41],"While":[42],"many":[43],"agentic":[44],"pipelines":[45],"mitigate":[46],"this":[47,54],"resetting":[49],"state":[50],"at":[51,62,101],"each":[52],"turn,":[53],"approach":[55],"discards":[56],"vital":[57],"context":[58,73],"impairs":[60],"performance":[61],"turn":[63],"onsets.":[64,103],"We":[65],"propose":[66],"two":[67,81,86],"state-management":[68],"strategies":[69],"preserve":[71],"cross-utterance":[72],"reduce":[75],"onset":[76],"errors.":[77],"In":[78],"experiments":[79],"with":[80],"state-of-the-art":[82],"spoken":[87],"dialogue":[88],"benchmarks,":[89],"our":[90],"best":[91],"method":[92],"yields":[93],"an":[94],"average":[95],"15-21%":[97],"relative":[98],"WER":[99],"reduction":[100],"utterance":[102]},"counts_by_year":[],"updated_date":"2026-10-17T09:40:24.721904","created_date":"2026-08-26T00:00:00"}