{"id":"https://openalex.org/W4415330331","doi":"https://doi.org/10.48550/arxiv.2506.00934","title":"GRAM: Spatial general-purpose audio representation models for real-world applications","display_name":"GRAM: Spatial general-purpose audio representation models for real-world applications","publication_year":2025,"publication_date":"2025-06-01","ids":{"openalex":"https://openalex.org/W4415330331","doi":"https://doi.org/10.48550/arxiv.2506.00934"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2506.00934","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.00934","pdf_url":"https://arxiv.org/pdf/2506.00934","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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.00934","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120055908","display_name":"Goksenin Yuksel","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I145872427","display_name":"Radboud University Nijmegen","ror":"https://ror.org/016xsfp80","country_code":"NL","type":"education","lineage":["https://openalex.org/I145872427"]},{"id":"https://openalex.org/I4405261313","display_name":"Donders Institute for Brain, Cognition and Behaviour","ror":"https://ror.org/053sba816","country_code":"NL","type":"facility","lineage":["https://openalex.org/I145872427","https://openalex.org/I4405261313"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Yuksel, Goksenin","raw_affiliation_strings":["Donders Institute , Radboud University , Nijmegen , The Nether- lands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Donders Institute , Radboud University , Nijmegen , The Nether- lands","institution_ids":["https://openalex.org/I145872427","https://openalex.org/I4405261313"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074794877","display_name":"Marcel A. J. van Gerven","orcid":"https://orcid.org/0000-0002-2206-9098","observed_orcids":["https://orcid.org/0000-0002-2206-9098"]},"institutions":[{"id":"https://openalex.org/I145872427","display_name":"Radboud University Nijmegen","ror":"https://ror.org/016xsfp80","country_code":"NL","type":"education","lineage":["https://openalex.org/I145872427"]},{"id":"https://openalex.org/I4405261313","display_name":"Donders Institute for Brain, Cognition and Behaviour","ror":"https://ror.org/053sba816","country_code":"NL","type":"facility","lineage":["https://openalex.org/I145872427","https://openalex.org/I4405261313"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"van Gerven, Marcel","raw_affiliation_strings":["Donders Institute , Radboud University , Nijmegen , The Nether- lands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Donders Institute , Radboud University , Nijmegen , The Nether- lands","institution_ids":["https://openalex.org/I145872427","https://openalex.org/I4405261313"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067480875","display_name":"Kiki van der Heijden","orcid":"https://orcid.org/0000-0003-4516-7907","observed_orcids":["https://orcid.org/0000-0003-4516-7907"]},"institutions":[{"id":"https://openalex.org/I145872427","display_name":"Radboud University Nijmegen","ror":"https://ror.org/016xsfp80","country_code":"NL","type":"education","lineage":["https://openalex.org/I145872427"]},{"id":"https://openalex.org/I4405261313","display_name":"Donders Institute for Brain, Cognition and Behaviour","ror":"https://ror.org/053sba816","country_code":"NL","type":"facility","lineage":["https://openalex.org/I145872427","https://openalex.org/I4405261313"]},{"id":"https://openalex.org/I4405270606","display_name":"Mortimer B. Zuckerman Mind Brain Behavior Institute","ror":"https://ror.org/0110mmp98","country_code":"US","type":"facility","lineage":["https://openalex.org/I4405270606"]},{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["NL","US"],"is_corresponding":false,"raw_author_name":"van der Heijden, Kiki","raw_affiliation_strings":["Donders Institute , Radboud University , Nijmegen , The Nether- lands","Mortimer B Zuckerman Institute , Columbia University , New York , United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Donders Institute , Radboud University , Nijmegen , The Nether- lands","institution_ids":["https://openalex.org/I145872427","https://openalex.org/I4405261313"]},{"raw_affiliation_string":"Mortimer B Zuckerman Institute , Columbia University , New York , United States","institution_ids":["https://openalex.org/I4405270606","https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"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/T11309","display_name":"Music and Audio Processing","score":0.8720999956130981,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.8720999956130981,"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/T10860","display_name":"Speech and Audio Processing","score":0.12470000237226486,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.0013000000035390258,"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/sound-localization","display_name":"sound localization","score":0.652999997138977},{"id":"https://openalex.org/keywords/reverberation","display_name":"reverberation","score":0.7979999780654907},{"id":"https://openalex.org/keywords/noise-robustness","display_name":"noise robustness","score":0.9279999732971191},{"id":"https://openalex.org/keywords/self-supervised-learning","display_name":"self-supervised learning","score":0.8640000224113464},{"id":"https://openalex.org/keywords/source-localization","display_name":"source localization","score":0.3440000116825104}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7093999981880188},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.6481000185012817},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.6151999831199646},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5950999855995178},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.516700029373169},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.47850000858306885},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.44519999623298645},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4372999966144562},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.39399999380111694},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.38269999623298645},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.365200012922287},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3456000089645386},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.33480000495910645},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.33399999141693115},{"id":"https://openalex.org/C2778488704","wikidata":"https://www.wikidata.org/wiki/Q15190726","display_name":"Audio equipment","level":2,"score":0.3327000141143799},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.3208000063896179},{"id":"https://openalex.org/C9940772","wikidata":"https://www.wikidata.org/wiki/Q557399","display_name":"Psychoacoustics","level":3,"score":0.31679999828338623},{"id":"https://openalex.org/C87687168","wikidata":"https://www.wikidata.org/wiki/Q173114","display_name":"Digital audio","level":4,"score":0.2953999936580658},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.295199990272522},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.28870001435279846},{"id":"https://openalex.org/C167940747","wikidata":"https://www.wikidata.org/wiki/Q63727227","display_name":"Audio signal flow","level":5,"score":0.28439998626708984},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.273499995470047},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.26980000734329224},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.2624000012874603},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.25220000743865967}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2506.00934","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.00934","pdf_url":"https://arxiv.org/pdf/2506.00934","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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2506.00934","doi":"https://doi.org/10.48550/arxiv.2506.00934","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.00934","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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2506.00934","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.00934","pdf_url":"https://arxiv.org/pdf/2506.00934","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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G6721024984","display_name":"Surrounded by sound: Deep neural network models of naturalistic spatial hearing.","funder_award_id":"VI.Veni.202.184","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"}],"funders":[{"id":"https://openalex.org/F4320321800","display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","ror":"https://ror.org/04jsz6e67"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415330331.pdf","grobid_xml":"https://content.openalex.org/works/W4415330331.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Audio":[0],"foundation":[1,45,91,133,180],"models":[2,20,46,92,134,181],"learn":[3,81],"general-purpose":[4,69],"audio":[5,28,44,71,83,90,132,179],"representations":[6],"that":[7,73,126],"facilitate":[8],"a":[9,68,75,94,146,173],"wide":[10],"range":[11],"of":[12,18,51,100,109,148],"downstream":[13],"tasks.":[14],"While":[15],"the":[16,48,138,149],"performance":[17,157],"these":[19,63,114],"has":[21],"greatly":[22],"increased":[23],"for":[24,182],"conventional":[25],"single-channel,":[26],"dry":[27],"clips,":[29],"their":[30],"success":[31],"in":[32,93,158,167],"real-world":[33,52,70,110,165,183],"acoustic":[34,53,103],"environments":[35,104,111,160],"with":[36],"reverberation":[37],"and":[38,88,112,121,137,161],"noise":[39],"is":[40],"limited.":[41],"Furthermore,":[42],"most":[43],"ignore":[47],"spatial":[49,82,102,178],"dimension":[50],"environments,":[54],"ruling":[55],"out":[56],"tasks":[57],"involving":[58],"sound":[59],"localization.":[60],"To":[61],"address":[62],"limitations,":[64],"we":[65],"propose":[66],"GRAM:":[67],"model":[72],"employs":[74],"multi-channel":[76],"masked":[77],"autoencoder":[78],"to":[79,164],"efficiently":[80,163],"representations.":[84],"We":[85],"evaluated":[86],"GRAM":[87,127,152,171],"other":[89],"standardized":[95],"manner":[96],"on":[97,135],"high-quality":[98],"simulations":[99],"naturalistic,":[101],"as":[105,107],"well":[106],"recordings":[108,166],"release":[113],"two":[115],"complementary":[116],"benchmark":[117],"task":[118],"suites:":[119],"NatHEAR":[120,136],"RealSELD.":[122,168],"Our":[123],"results":[124],"demonstrate":[125],"outperforms":[128],"all":[129],"state-of-the-art":[130,155],"self-supervised":[131],"clean,":[139],"single-channel":[140],"version":[141],"HEAR,":[142],"while":[143],"using":[144],"only":[145],"fraction":[147],"training":[150],"data.":[151],"also":[153],"shows":[154],"localization":[156],"simulated":[159],"generalizes":[162],"Taken":[169],"together,":[170],"presents":[172],"significant":[174],"advance":[175],"toward":[176],"robust":[177],"environments.":[184]},"counts_by_year":[],"updated_date":"2026-10-08T09:06:37.294493","created_date":"2025-10-19T00:00:00"}
