{"id":"https://openalex.org/W4412945028","doi":"https://doi.org/10.18653/v1/2025.acl-long.818","title":"VoxEval: Benchmarking the Knowledge Understanding Capabilities of End-to-End Spoken Language Models","display_name":"VoxEval: Benchmarking the Knowledge Understanding Capabilities of End-to-End Spoken Language Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412945028","doi":"https://doi.org/10.18653/v1/2025.acl-long.818"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.818","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.818","pdf_url":"https://aclanthology.org/2025.acl-long.818.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.818.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014251650","display_name":"Wenqian Cui","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenqian Cui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101038769","display_name":"Xiaoqi Jiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoqi Jiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027386336","display_name":"Ziqiao Meng","orcid":"https://orcid.org/0000-0002-0231-5992"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ziqiao Meng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5042251906","display_name":"Irwin King","orcid":"https://orcid.org/0000-0001-8106-6447"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Irwin King","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":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"16735","last_page":"16753"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9718000292778015,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9718000292778015,"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":0.9348000288009644,"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":0.9283000230789185,"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/benchmarking","display_name":"Benchmarking","score":0.7670515775680542},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7667897939682007},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6345366835594177},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.6105865836143494},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.47173941135406494},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36905768513679504},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.0591789186000824}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.7670515775680542},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7667897939682007},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6345366835594177},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.6105865836143494},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47173941135406494},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36905768513679504},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0591789186000824},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.818","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.818","pdf_url":"https://aclanthology.org/2025.acl-long.818.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.818","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.818","pdf_url":"https://aclanthology.org/2025.acl-long.818.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7400000095367432,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322942","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412945028.pdf","grobid_xml":"https://content.openalex.org/works/W4412945028.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W1490753184","https://openalex.org/W2284465472","https://openalex.org/W2291782699","https://openalex.org/W1993948687","https://openalex.org/W2000169967","https://openalex.org/W3204019825"],"abstract_inverted_index":{"With":[0],"the":[1,100,130,144],"rising":[2],"need":[3,131],"for":[4,25,53,83],"speech-based":[5],"interaction":[6],"models,":[7],"end-to-end":[8,48],"Spoken":[9],"Language":[10],"Models":[11],"(SLMs)":[12],"have":[13],"emerged":[14],"as":[15],"a":[16,64],"promising":[17],"solution.While":[18],"these":[19,59],"models":[20],"require":[21],"comprehensive":[22],"world":[23],"knowledge":[24,40,71],"meaningful":[26],"and":[27,51,86,97,128,149],"reliable":[28,150],"human":[29],"interactions,":[30],"existing":[31],"questionanswering":[32],"(QA)":[33],"benchmarks":[34],"fall":[35],"short":[36],"in":[37,108,136],"evaluating":[38],"SLMs'":[39,70],"understanding":[41,72],"due":[42],"to":[43,46,118,124,132],"their":[44,122],"inability":[45],"support":[47],"speech":[49,75,81],"evaluation":[50,111],"account":[52],"varied":[54],"input":[55,94],"audio":[56,95,126],"conditions.To":[57],"address":[58],"limitations,":[60],"we":[61],"present":[62],"VoxEval,":[63],"novel":[65],"SpeechQA":[66],"benchmark":[67,77,141],"that":[68,113],"assesses":[69],"through":[73],"pure":[74],"interactions.Our":[76],"1)":[78],"uniquely":[79],"maintains":[80],"format":[82],"both":[84],"inputs":[85],"outputs,":[87],"2)":[88],"evaluates":[89],"model":[90],"robustness":[91],"across":[92],"diverse":[93],"conditions,":[96],"3)":[98],"pioneers":[99],"assessment":[101],"of":[102,146],"complex":[103],"tasks":[104],"like":[105],"mathematical":[106],"reasoning":[107,134],"spoken":[109],"format.Systematic":[110],"demonstrates":[112],"VoxEval":[114],"presents":[115],"significant":[116],"challenges":[117],"current":[119],"SLMs,":[120],"revealing":[121],"sensitivity":[123],"varying":[125],"conditions":[127],"highlighting":[129],"enhance":[133],"capabilities":[135],"future":[137],"development.We":[138],"hope":[139],"this":[140],"could":[142],"guide":[143],"advancement":[145],"more":[147],"sophisticated":[148],"SLMs.":[151]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}