{"id":"https://openalex.org/W7214748679","doi":"https://doi.org/10.48550/arxiv.2609.32607","title":"VoxMem: Benchmarking Multimodal Memory in Large Audio Language Models","display_name":"VoxMem: Benchmarking Multimodal Memory in Large Audio Language Models","publication_year":2026,"publication_date":"2026-09-26","ids":{"openalex":"https://openalex.org/W7214748679","doi":"https://doi.org/10.48550/arxiv.2609.32607"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.32607","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.32607","pdf_url":"https://arxiv.org/pdf/2609.32607","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":"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/2609.32607","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5153483176","display_name":"Yang Xiao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xiao, Yang","raw_affiliation_strings":["University of Melbourne"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Melbourne","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032689109","display_name":"Vidhyasaharan Sethu","orcid":"https://orcid.org/0000-0001-8492-1787","observed_orcids":["https://orcid.org/0000-0001-8492-1787"]},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Sethu, Vidhyasaharan","raw_affiliation_strings":["University of New South Wales"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of New South Wales","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060545335","display_name":"Eun\u2010Jung Holden","orcid":"https://orcid.org/0000-0002-8752-1639","observed_orcids":["https://orcid.org/0000-0002-8752-1639"]},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Holden, Eun-Jung","raw_affiliation_strings":["University of Melbourne"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Melbourne","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071116593","display_name":"Ting Dang","orcid":"https://orcid.org/0000-0003-3806-1493","observed_orcids":["https://orcid.org/0000-0003-3806-1493"]},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Dang, Ting","raw_affiliation_strings":["University of Melbourne"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Melbourne","institution_ids":["https://openalex.org/I165779595"]}]}],"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":1,"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/T12031","display_name":"Speech and dialogue systems","score":0.899399995803833,"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/T12031","display_name":"Speech and dialogue systems","score":0.899399995803833,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.09200000017881393,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.0024999999441206455,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/multimodal-memory","display_name":"multimodal memory","score":0.8009999990463257},{"id":"https://openalex.org/keywords/large-audio-language-models","display_name":"large audio language models","score":0.9309999942779541},{"id":"https://openalex.org/keywords/speaker-identity","display_name":"speaker identity","score":0.5440000295639038},{"id":"https://openalex.org/keywords/paralinguistic-cues","display_name":"paralinguistic cues","score":0.9819999933242798},{"id":"https://openalex.org/keywords/environmental-sounds","display_name":"environmental sounds","score":0.8209999799728394},{"id":"https://openalex.org/keywords/temporal-tracking","display_name":"temporal tracking","score":0.9369999766349792},{"id":"https://openalex.org/keywords/information-extraction","display_name":"information extraction","score":0.6470000147819519}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7785000205039978},{"id":"https://openalex.org/C133378560","wikidata":"https://www.wikidata.org/wiki/Q1753225","display_name":"Paralanguage","level":2,"score":0.6373999714851379},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5292999744415283},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.4943000078201294},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46560001373291016},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.45210000872612},{"id":"https://openalex.org/C2780876879","wikidata":"https://www.wikidata.org/wiki/Q3054749","display_name":"Meaning (existential)","level":2,"score":0.43689998984336853},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.40549999475479126},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4018000066280365},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3684999942779541},{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.34360000491142273},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.3328000009059906},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.31540000438690186},{"id":"https://openalex.org/C88576662","wikidata":"https://www.wikidata.org/wiki/Q18646","display_name":"Episodic memory","level":3,"score":0.30889999866485596},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.30390000343322754},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.2939000129699707},{"id":"https://openalex.org/C2985957978","wikidata":"https://www.wikidata.org/wiki/Q492","display_name":"Human memory","level":3,"score":0.28209999203681946},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.27459999918937683},{"id":"https://openalex.org/C169087156","wikidata":"https://www.wikidata.org/wiki/Q2131593","display_name":"Framing (construction)","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.271699994802475},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.26980000734329224},{"id":"https://openalex.org/C21963081","wikidata":"https://www.wikidata.org/wiki/Q11337567","display_name":"Working memory","level":3,"score":0.26350000500679016},{"id":"https://openalex.org/C12186640","wikidata":"https://www.wikidata.org/wiki/Q6815743","display_name":"Memory model","level":3,"score":0.2614000141620636},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.2605000138282776},{"id":"https://openalex.org/C76679254","wikidata":"https://www.wikidata.org/wiki/Q5165163","display_name":"Context-dependent memory","level":4,"score":0.25839999318122864},{"id":"https://openalex.org/C2777672088","wikidata":"https://www.wikidata.org/wiki/Q1441804","display_name":"Pitch accent","level":3,"score":0.25769999623298645},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.25600001215934753},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.32607","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.32607","pdf_url":"https://arxiv.org/pdf/2609.32607","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.32607","doi":"https://doi.org/10.48550/arxiv.2609.32607","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.32607","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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.32607","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.32607","pdf_url":"https://arxiv.org/pdf/2609.32607","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":"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/W7214748679.pdf","grobid_xml":"https://content.openalex.org/works/W7214748679.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7214702473","https://openalex.org/W7206186710","https://openalex.org/W7204606869","https://openalex.org/W7119534494","https://openalex.org/W7162515554","https://openalex.org/W7214014402","https://openalex.org/W7204946435","https://openalex.org/W7213584858","https://openalex.org/W4402111627","https://openalex.org/W7155518086"],"abstract_inverted_index":{"Spoken":[0],"conversational":[1,263],"systems":[2],"must":[3],"recover":[4],"information":[5,13,33,76],"from":[6,45,195],"prior":[7],"interactions":[8,70],"(i.e.,":[9],"memory),":[10],"yet":[11],"relevant":[12],"in":[14,37,187],"speech":[15],"extends":[16],"beyond":[17],"what":[18,30,49,211,222],"was":[19,27,31,212,223],"said":[20,23,213,218],"to":[21,50,127,134,197,248,252],"who":[22,217],"it,":[24,135,219],"how":[25],"it":[26],"spoken,":[28],"and":[29,41,103,108,130,136,183,190,236,254],"audible,":[32,224],"that":[34,117,227],"exists":[35],"only":[36],"the":[38,124,131,258],"audio":[39],"signal":[40],"cannot":[42],"be":[43,128],"recovered":[44],"a":[46,58,83,112,138,225,250],"transcript.":[47],"Beyond":[48],"remember,":[51],"memory":[52,106,110,119,175],"also":[53],"demands":[54],"diverse":[55],"operations:":[56],"retrieving":[57],"single":[59,84],"fact,":[60],"integrating":[61],"evidence":[62,126,163,244],"across":[63,73,78,192,243],"turns,":[64],"tracking":[65],"an":[66],"evolving":[67],"state.":[68],"Real":[69],"further":[71],"unfold":[72],"sessions,":[74],"meaning":[75],"accumulates":[77],"distinct":[79,240],"episodes":[80],"rather":[81],"than":[82,216],"continuous":[85],"recording.":[86],"Existing":[87],"benchmarks":[88],"fall":[89],"short":[90],"on":[91,98,145,257],"all":[92],"three":[93],"dimensions:":[94],"they":[95],"focus":[96],"primarily":[97],"lexical":[99],"content,":[100],"adopt":[101],"limited":[102],"ad":[104],"hoc":[105],"operations,":[107,231],"treat":[109],"as":[111,238],"single-session":[113],"problem.":[114],"We":[115],"argue":[116],"principled":[118],"evaluation":[120,152],"requires":[121],"jointly":[122],"characterizing":[123],"acoustic":[125,162],"retained":[129],"operations":[132,176],"applied":[133],"introduce":[137],"taxonomy":[139],"along":[140],"these":[141],"two":[142],"axes.":[143],"Building":[144],"this":[146],"taxonomy,":[147],"we":[148],"present":[149],"VoxMem:":[150],"3,196":[151],"instances":[153],"over":[154],"34,743":[155],"spoken":[156,262],"sessions":[157],"(177":[158],"hours)":[159],"crossing":[160],"four":[161,174],"types":[164],"(speech":[165],"semantics,":[166],"speaker":[167],"identity,":[168],"paralinguistic":[169],"cues,":[170],"environmental":[171],"sound)":[172],"with":[173,233],"(information":[177],"extraction,":[178],"multi-session":[179,188],"reasoning,":[180],"temporal":[181],"tracking,":[182],"answer":[184],"refusal),":[185],"grounded":[186],"histories":[189],"stratified":[191],"context":[193],"budgets":[194],"8K":[196],"64K":[198],"tokens.":[199],"Evaluating":[200],"15":[201],"LALMs,":[202],"no":[203],"model":[204],"exceeds":[205],"40%":[206],"at":[207],"32K.":[208],"Models":[209],"retain":[210],"far":[214],"better":[215],"how,":[220],"or":[221],"gap":[226],"widens":[228],"for":[229],"complex":[230],"grows":[232],"history":[234],"length,":[235],"manifests":[237],"qualitatively":[239],"failure":[241],"modes":[242],"types.":[245],"VoxMem":[246],"aims":[247],"provide":[249],"foundation":[251],"measure":[253],"drive":[255],"progress":[256],"full":[259],"scope":[260],"of":[261],"memory.":[264]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-09-30T00:00:00"}