{"id":"https://openalex.org/W7148445182","doi":"https://doi.org/10.1109/asru65441.2025.11434725","title":"AURA: Agent for Understanding, Reasoning, and Automated Tool Use in Voice-Driven Tasks","display_name":"AURA: Agent for Understanding, Reasoning, and Automated Tool Use in Voice-Driven Tasks","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148445182","doi":"https://doi.org/10.1109/asru65441.2025.11434725"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434725","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434725","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/A5120371850","display_name":"Leander Melroy Maben","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Leander Melroy Maben","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132795863","display_name":"Gayathri Ganesh Lakshmy","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gayathri Ganesh Lakshmy","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038786982","display_name":"S. Radhakrishnan","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Srijith Radhakrishnan","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047892839","display_name":"Siddhant Arora","orcid":"https://orcid.org/0000-0003-0375-496X"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siddhant Arora","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132789061","display_name":"Shinji Watanabe","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5120371850"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87566307,"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/T12128","display_name":"AI in Service Interactions","score":0.31769999861717224,"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/T12128","display_name":"AI in Service Interactions","score":0.31769999861717224,"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":0.2597000002861023,"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/T10028","display_name":"Topic Modeling","score":0.11089999973773956,"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/pipeline","display_name":"Pipeline (software)","score":0.7024999856948853},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6498000025749207},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.590499997138977},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5044000148773193},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.475600004196167},{"id":"https://openalex.org/keywords/invocation","display_name":"Invocation","score":0.34459999203681946},{"id":"https://openalex.org/keywords/user-interface","display_name":"User interface","score":0.34220001101493835},{"id":"https://openalex.org/keywords/web-application","display_name":"Web application","score":0.335099995136261}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.746999979019165},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7024999856948853},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6498000025749207},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.6121000051498413},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.590499997138977},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5044000148773193},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.475600004196167},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36010000109672546},{"id":"https://openalex.org/C2776527387","wikidata":"https://www.wikidata.org/wiki/Q1671839","display_name":"Invocation","level":2,"score":0.34459999203681946},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.34220001101493835},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.335099995136261},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.33410000801086426},{"id":"https://openalex.org/C2777350023","wikidata":"https://www.wikidata.org/wiki/Q1154226","display_name":"Aura","level":3,"score":0.3237000107765198},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.31450000405311584},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3068000078201294},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.2987000048160553},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.29190000891685486},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2912999987602234},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.28600001335144043},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2597000002861023},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.2533000111579895}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434725","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434725","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":[{"display_name":"Quality Education","score":0.5666804909706116,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W2890894339","https://openalex.org/W2964006684","https://openalex.org/W3016160783","https://openalex.org/W4387321091"],"related_works":[],"abstract_inverted_index":{"Despite":[0],"advances":[1],"in":[2,58],"language":[3,86],"and":[4,19,29,48,56,62,73,88,102],"speech":[5,123],"technologies,":[6],"no":[7],"open-source":[8],"system":[9],"enables":[10],"full":[11],"speech-to-speech,":[12],"multiturn":[13],"dialogue":[14],"with":[15,109],"integrated":[16],"tool":[17,46],"use":[18],"agentic":[20],"reasoning.":[21],"We":[22],"introduce":[23],"AURA":[24,51,93],"(Agent":[25],"for":[26],"Understanding,":[27],"Reasoning,":[28],"Automated":[30],"Tool":[31],"Use),":[32],"the":[33],"first":[34],"open-source,":[35],"speech-native":[36],"assistant":[37],"capable":[38],"of":[39,81],"completing":[40],"complex,":[41,121],"goal-driven":[42],"tasks":[43],"through":[44],"dynamic":[45],"invocation":[47],"multi-turn":[49,122],"conversation.":[50],"combines":[52],"open-weight":[53,100],"ASR,":[54],"TTS,":[55],"LLMs":[57],"a":[59],"cascaded":[60],"pipeline":[61],"supports":[63],"tools":[64,83],"such":[65],"as":[66],"calendar":[67],"booking,":[68],"contact":[69],"lookup,":[70],"web":[71],"search,":[72],"email.":[74],"Its":[75],"modular":[76],"design":[77],"allows":[78],"easy":[79],"integration":[80],"new":[82],"using":[84],"natural":[85],"prompts":[87],"action":[89],"classes.":[90],"On":[91],"VoiceBench,":[92],"scores":[94],"$92.75":[95],"\\%$":[96,117],"on":[97,106,120],"Open-BookQA\u2014outperforming":[98],"all":[99],"systems":[101],"nearing":[103],"GPT-4o\u2014and":[104],"4.39":[105],"AlpacaEval,":[107],"competitive":[108],"other":[110],"openweight":[111],"systems.":[112],"Human":[113],"evaluation":[114],"shows":[115],"$90":[116],"task":[118],"success":[119],"tasks.":[124]},"counts_by_year":[],"updated_date":"2026-04-03T16:44:17.987007","created_date":"2026-04-03T00:00:00"}
