{"id":"https://openalex.org/W7148277713","doi":"https://doi.org/10.1109/asru65441.2025.11434669","title":"Open Full-duplex Voice Agent with Speech-to-Speech Language Model","display_name":"Open Full-duplex Voice Agent with Speech-to-Speech Language Model","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148277713","doi":"https://doi.org/10.1109/asru65441.2025.11434669"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434669","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434669","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025318789","display_name":"Edresson Casanova","orcid":"https://orcid.org/0000-0003-0160-7173"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Edresson Casanova","raw_affiliation_strings":["NVIDIA"],"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132795805","display_name":"Chen Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen Chen","raw_affiliation_strings":["NVIDIA"],"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132790536","display_name":"Kevin Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kevin Hu","raw_affiliation_strings":["NVIDIA"],"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132822940","display_name":"Ankita Pasad","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ankita Pasad","raw_affiliation_strings":["NVIDIA"],"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007900374","display_name":"Elena Rastorgueva","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Elena Rastorgueva","raw_affiliation_strings":["NVIDIA"],"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132773062","display_name":"Seelan Lakshmi Narasimhan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Seelan Lakshmi Narasimhan","raw_affiliation_strings":["NVIDIA"],"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083696320","display_name":"Slyne Deng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Slyne Deng","raw_affiliation_strings":["NVIDIA"],"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020404017","display_name":"Ehsan Hosseini-Asl","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ehsan Hosseini-Asl","raw_affiliation_strings":["NVIDIA"],"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127116251","display_name":"Piotr \u017belasko","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Piotr Zelasko","raw_affiliation_strings":["NVIDIA"],"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042701876","display_name":"Valentin Mendelev","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Valentin Mendelev","raw_affiliation_strings":["NVIDIA"],"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101935896","display_name":"Subhankar Ghosh","orcid":"https://orcid.org/0000-0001-9191-5684"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Subhankar Ghosh","raw_affiliation_strings":["NVIDIA"],"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132800262","display_name":"Yifan Peng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yifan Peng","raw_affiliation_strings":["NVIDIA"],"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132798240","display_name":"Zhehuai Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhehuai Chen","raw_affiliation_strings":["NVIDIA"],"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100762970","display_name":"Jason Li","orcid":"https://orcid.org/0000-0002-1150-3549"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jason Li","raw_affiliation_strings":["NVIDIA"],"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132804247","display_name":"Jagadeesh Balam","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jagadeesh Balam","raw_affiliation_strings":["NVIDIA"],"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026088310","display_name":"Vitaly Lavrukhin","orcid":"https://orcid.org/0009-0006-7866-8301"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vitaly Lavrukhin","raw_affiliation_strings":["NVIDIA"],"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132800911","display_name":"Boris Ginsburg","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Boris Ginsburg","raw_affiliation_strings":["NVIDIA"],"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":17,"corresponding_author_ids":["https://openalex.org/A5025318789"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87549034,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.4027000069618225,"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":0.4027000069618225,"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":0.20659999549388885,"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":0.08569999784231186,"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/language-model","display_name":"Language model","score":0.3903000056743622},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.34209999442100525},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2727999985218048},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.2718000113964081},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.27149999141693115},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.2685000002384186}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6187000274658203},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.399399995803833},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3903000056743622},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38690000772476196},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35260000824928284},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.34209999442100525},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.31850001215934753},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.2921000123023987},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2727999985218048},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2718000113964081},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.27149999141693115},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.2685000002384186},{"id":"https://openalex.org/C179603123","wikidata":"https://www.wikidata.org/wiki/Q1941921","display_name":"Modeling language","level":3,"score":0.266400009393692},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.25999999046325684},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.25929999351501465}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434669","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434669","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W4225956675","https://openalex.org/W4307680525","https://openalex.org/W4389524500","https://openalex.org/W4392903872","https://openalex.org/W4392903956","https://openalex.org/W4393178509","https://openalex.org/W4402111234","https://openalex.org/W4412945230","https://openalex.org/W4415433511","https://openalex.org/W7133227460"],"related_works":[],"abstract_inverted_index":{"We":[0],"present":[1],"the":[2,78],"system":[3],"demonstration":[4],"and":[5,46,62,71],"opensource":[6],"code":[7],"release":[8],"of":[9],"a":[10,24,60,90],"novel,":[11],"data-efficient":[12],"framework":[13],"that":[14],"converts":[15],"any":[16,41],"standard":[17],"text":[18],"Large":[19],"Language":[20],"Model":[21],"(LLM)":[22],"into":[23],"full-duplex":[25,63],"end-to-end":[26,92],"(E2E)":[27],"speech-to-speech":[28],"(S2S)":[29],"model,":[30],"for":[31,82],"building":[32],"conversational":[33],"voice":[34,64,86],"agents.":[35],"Our":[36],"new":[37],"modeling":[38],"method":[39],"enables":[40],"LLMs":[42],"to":[43,57,80],"simultaneously":[44],"listen":[45],"speak":[47],"without":[48],"requiring":[49],"extensive":[50],"speech-text":[51],"pretraining.":[52],"Moreover,":[53],"we":[54],"demonstrate":[55],"how":[56],"put":[58],"together":[59],"low-latency":[61],"agent":[65],"with":[66],"open-source":[67,96],"modeling,":[68],"inference":[69],"optimization,":[70],"serving":[72],"solutions.":[73],"This":[74],"work":[75],"significantly":[76],"lowers":[77],"barrier":[79],"entry":[81],"developing":[83],"low-latency,":[84],"human-like":[85],"agents":[87],"by":[88],"providing":[89],"generalizable,":[91],"solution":[93],"built":[94],"on":[95],"technologies.":[97]},"counts_by_year":[],"updated_date":"2026-04-03T16:44:17.987007","created_date":"2026-04-03T00:00:00"}