{"id":"https://openalex.org/W7141539971","doi":"https://doi.org/10.48550/arxiv.2603.25727","title":"Back to Basics: Revisiting ASR in the Age of Voice Agents","display_name":"Back to Basics: Revisiting ASR in the Age of Voice Agents","publication_year":2026,"publication_date":"2026-03-26","ids":{"openalex":"https://openalex.org/W7141539971","doi":"https://doi.org/10.48550/arxiv.2603.25727"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2603.25727","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2603.25727","pdf_url":"https://arxiv.org/pdf/2603.25727","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/2603.25727","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130778512","display_name":"Geeyang Tay","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tay, Geeyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130769824","display_name":"Wentao Ma","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Wentao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138721918","display_name":"Jaewon Lee","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lee, Jaewon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113013345","display_name":"Yuzhi Tang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Yuzhi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130773340","display_name":"Daniel Lee","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lee, Daniel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130767343","display_name":"Weisu Yin","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yin, Weisu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130816695","display_name":"Dongming Shen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shen, Dongming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130725552","display_name":"Silin Meng","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meng, Silin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130775105","display_name":"Yi Zhu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Yi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130828736","display_name":"Mu Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Mu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5130721492","display_name":"Alex Smola","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Smola, Alex","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":5,"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":0.9994999766349792,"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":0.9994999766349792,"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":9.999999747378752e-05,"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":9.999999747378752e-05,"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/speech-recognition","display_name":"speech recognition","score":0.9879999756813049},{"id":"https://openalex.org/keywords/voice-assistants","display_name":"voice assistants","score":0.8130000233650208},{"id":"https://openalex.org/keywords/diagnostic-benchmark","display_name":"diagnostic benchmark","score":0.7879999876022339},{"id":"https://openalex.org/keywords/multilingual-speech","display_name":"multilingual speech","score":0.5950000286102295},{"id":"https://openalex.org/keywords/environmental-degradation","display_name":"environmental degradation","score":0.7799999713897705},{"id":"https://openalex.org/keywords/demographic-change","display_name":"demographic change","score":0.8339999914169312},{"id":"https://openalex.org/keywords/linguistic-diversity","display_name":"linguistic diversity","score":0.9679999947547913},{"id":"https://openalex.org/keywords/hallucinations","display_name":"hallucinations","score":0.9129999876022339},{"id":"https://openalex.org/keywords/safety-risk","display_name":"safety risk","score":0.5479999780654907}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7947999835014343},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6786999702453613},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5663999915122986},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.45329999923706055},{"id":"https://openalex.org/C2911011789","wikidata":"https://www.wikidata.org/wiki/Q130741","display_name":"Hallucinating","level":2,"score":0.4505000114440918},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44130000472068787},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.43619999289512634},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4359999895095825},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4284000098705292},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4117000102996826},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.33079999685287476},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32760000228881836},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.2728999853134155},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2705000042915344},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.2538999915122986}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2603.25727","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2603.25727","pdf_url":"https://arxiv.org/pdf/2603.25727","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.2603.25727","doi":"https://doi.org/10.48550/arxiv.2603.25727","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.25727","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:2603.25727","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2603.25727","pdf_url":"https://arxiv.org/pdf/2603.25727","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7141539971.pdf","grobid_xml":"https://content.openalex.org/works/W7141539971.grobid-xml"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W2763188033","https://openalex.org/W2799473636","https://openalex.org/W2995929068","https://openalex.org/W3036601975","https://openalex.org/W3093579165","https://openalex.org/W3095410713","https://openalex.org/W3097777922","https://openalex.org/W3210096903","https://openalex.org/W4311000453","https://openalex.org/W4319862635","https://openalex.org/W4378105483","https://openalex.org/W4381827575","https://openalex.org/W4387891768","https://openalex.org/W4388718054","https://openalex.org/W4391158821","https://openalex.org/W4392822074","https://openalex.org/W4393178509","https://openalex.org/W4400717319","https://openalex.org/W4402112175","https://openalex.org/W4403883071","https://openalex.org/W4404261856","https://openalex.org/W4404311027","https://openalex.org/W4404784428","https://openalex.org/W4405057125","https://openalex.org/W4408352010","https://openalex.org/W4408352589","https://openalex.org/W4412944702","https://openalex.org/W4412945284","https://openalex.org/W4414820366","https://openalex.org/W4414888144","https://openalex.org/W4415032283","https://openalex.org/W4415318706","https://openalex.org/W4415329203","https://openalex.org/W4415433608","https://openalex.org/W4415879968","https://openalex.org/W4415897912","https://openalex.org/W4416061002","https://openalex.org/W4416338900","https://openalex.org/W6891931817","https://openalex.org/W6929476346","https://openalex.org/W6948369276","https://openalex.org/W7118277898","https://openalex.org/W7125488158","https://openalex.org/W7135017727"],"related_works":["https://openalex.org/W7077852211","https://openalex.org/W4392822074","https://openalex.org/W7161777482","https://openalex.org/W4408355549","https://openalex.org/W7152996602","https://openalex.org/W7047125562","https://openalex.org/W4405925569","https://openalex.org/W7166700973","https://openalex.org/W7221770279","https://openalex.org/W7168106144"],"abstract_inverted_index":{"Automatic":[0],"speech":[1,63],"recognition":[2],"(ASR)":[3],"systems":[4],"have":[5],"achieved":[6],"near-human":[7],"accuracy":[8],"on":[9],"curated":[10],"benchmarks,":[11],"yet":[12],"still":[13],"fail":[14],"in":[15,41,137],"real-world":[16],"voice":[17],"agents":[18],"under":[19,109],"conditions":[20],"that":[21,31,64,125,150],"current":[22],"evaluations":[23],"do":[24],"not":[25,95],"systematically":[26],"cover.":[27],"Without":[28],"diagnostic":[29,56],"tools":[30,149],"isolate":[32],"specific":[33],"failure":[34],"factors,":[35],"practitioners":[36,151],"cannot":[37],"anticipate":[38],"which":[39,42],"conditions,":[40],"languages,":[43],"will":[44],"cause":[45],"what":[46],"degree":[47],"of":[48],"degradation.":[49],"We":[50],"introduce":[51],"WildASR,":[52],"a":[53],"multilingual":[54],"(four-language)":[55],"benchmark":[57,142],"sourced":[58],"entirely":[59],"from":[60],"real":[61],"human":[62],"factorizes":[65],"ASR":[66,82,135],"robustness":[67,93],"along":[68],"three":[69,147],"axes:":[70],"environmental":[71],"degradation,":[72,90],"demographic":[73],"shift,":[74],"and":[75,87,91,133],"linguistic":[76],"diversity.":[77],"Evaluating":[78],"seven":[79],"widely":[80],"used":[81],"systems,":[83],"we":[84,144],"find":[85],"severe":[86],"uneven":[88],"performance":[89],"model":[92],"does":[94],"transfer":[96],"across":[97],"languages":[98],"or":[99,111],"conditions.":[100],"Critically,":[101],"models":[102],"often":[103],"hallucinate":[104],"plausible":[105],"but":[106],"unspoken":[107],"content":[108],"partial":[110],"degraded":[112],"inputs,":[113],"creating":[114],"concrete":[115],"safety":[116],"risks":[117],"for":[118,131],"downstream":[119],"agent":[120],"behavior.":[121],"Our":[122],"results":[123],"demonstrate":[124],"targeted,":[126],"factor-isolated":[127],"evaluation":[128],"is":[129],"essential":[130],"understanding":[132],"improving":[134],"reliability":[136],"production":[138],"systems.":[139],"Besides":[140],"the":[141],"itself,":[143],"also":[145],"present":[146],"analytical":[148],"can":[152],"use":[153],"to":[154],"guide":[155],"deployment":[156],"decisions.":[157]},"counts_by_year":[{"year":2026,"cited_by_count":5}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-03-28T00:00:00"}