{"id":"https://openalex.org/W4413156140","doi":"https://doi.org/10.1109/jproc.2025.3593952","title":"Computer Audition: From Task-Specific Machine Learning to Foundation Models","display_name":"Computer Audition: From Task-Specific Machine Learning to Foundation Models","publication_year":2025,"publication_date":"2025-04-01","ids":{"openalex":"https://openalex.org/W4413156140","doi":"https://doi.org/10.1109/jproc.2025.3593952"},"language":"en","primary_location":{"id":"doi:10.1109/jproc.2025.3593952","is_oa":true,"landing_page_url":"https://doi.org/10.1109/jproc.2025.3593952","pdf_url":null,"source":{"id":"https://openalex.org/S68686220","display_name":"Proceedings of the IEEE","issn_l":"0018-9219","issn":["0018-9219","1558-2256"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"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 IEEE","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/jproc.2025.3593952","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012240826","display_name":"Andreas Triantafyllopoulos","orcid":"https://orcid.org/0000-0001-8338-617X"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Andreas Triantafyllopoulos","raw_affiliation_strings":["Chair of Health Informatics (CHI), TUM University Hospital, Munich, Germany"],"raw_orcid":"https://orcid.org/0000-0001-8338-617X","affiliations":[{"raw_affiliation_string":"Chair of Health Informatics (CHI), TUM University Hospital, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092639661","display_name":"Iosif Tsangko","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Iosif Tsangko","raw_affiliation_strings":["Chair of Health Informatics (CHI), TUM University Hospital, Munich, Germany"],"raw_orcid":"https://orcid.org/0009-0007-9614-5894","affiliations":[{"raw_affiliation_string":"Chair of Health Informatics (CHI), TUM University Hospital, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023952045","display_name":"Alexander Gebhard","orcid":"https://orcid.org/0000-0003-4169-5403"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alexander Gebhard","raw_affiliation_strings":["Chair of Health Informatics (CHI), TUM University Hospital, Munich, Germany"],"raw_orcid":"https://orcid.org/0000-0003-4169-5403","affiliations":[{"raw_affiliation_string":"Chair of Health Informatics (CHI), TUM University Hospital, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079981416","display_name":"Annamaria Mesaros","orcid":"https://orcid.org/0000-0002-6640-9752"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Annamaria Mesaros","raw_affiliation_strings":["Audio Research Group, Tampere University, Tampere, Finland"],"raw_orcid":"https://orcid.org/0000-0002-6640-9752","affiliations":[{"raw_affiliation_string":"Audio Research Group, Tampere University, Tampere, Finland","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049691461","display_name":"Tuomas Virtanen","orcid":"https://orcid.org/0000-0002-4604-9729"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Tuomas Virtanen","raw_affiliation_strings":["Audio Research Group, Tampere University, Tampere, Finland"],"raw_orcid":"https://orcid.org/0000-0002-4604-9729","affiliations":[{"raw_affiliation_string":"Audio Research Group, Tampere University, Tampere, Finland","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043060302","display_name":"Bj\u00f6rn W. Schuller","orcid":"https://orcid.org/0000-0002-6478-8699"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bj\u00f6rn W. Schuller","raw_affiliation_strings":["Chair of Health Informatics (CHI), TUM University Hospital, Munich, Germany"],"raw_orcid":"https://orcid.org/0000-0002-6478-8699","affiliations":[{"raw_affiliation_string":"Chair of Health Informatics (CHI), TUM University Hospital, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5012240826"],"corresponding_institution_ids":["https://openalex.org/I62916508"],"apc_list":null,"apc_paid":null,"fwci":10.8663,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.98064824,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"113","issue":"4","first_page":"317","last_page":"343"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.7276999950408936,"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/T10320","display_name":"Neural Networks and Applications","score":0.7276999950408936,"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/foundation","display_name":"Foundation (evidence)","score":0.7957214713096619},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6593214273452759},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6002568006515503},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45155394077301025},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3786082863807678},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3299356698989868},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3249393701553345},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1656716763973236},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.08047729730606079},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.04801332950592041}],"concepts":[{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.7957214713096619},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6593214273452759},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6002568006515503},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45155394077301025},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3786082863807678},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3299356698989868},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3249393701553345},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1656716763973236},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.08047729730606079},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.04801332950592041},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/jproc.2025.3593952","is_oa":true,"landing_page_url":"https://doi.org/10.1109/jproc.2025.3593952","pdf_url":null,"source":{"id":"https://openalex.org/S68686220","display_name":"Proceedings of the IEEE","issn_l":"0018-9219","issn":["0018-9219","1558-2256"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"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 IEEE","raw_type":"journal-article"},{"id":"pmh:oai:mediatum.ub.tum.de:node/1795937","is_oa":false,"landing_page_url":"https://mediatum.ub.tum.de/1795937","pdf_url":null,"source":{"id":"https://openalex.org/S4377196330","display_name":"mediaTUM  (Technical University of Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"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":"article"},{"id":"pmh:oai:trepo.tuni.fi:10024/230552","is_oa":true,"landing_page_url":"https://trepo.tuni.fi/handle/10024/230552","pdf_url":null,"source":{"id":"https://openalex.org/S7407055260","display_name":"Trepo - Institutional Repository of Tampere University","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"reviewarticle"}],"best_oa_location":{"id":"doi:10.1109/jproc.2025.3593952","is_oa":true,"landing_page_url":"https://doi.org/10.1109/jproc.2025.3593952","pdf_url":null,"source":{"id":"https://openalex.org/S68686220","display_name":"Proceedings of the IEEE","issn_l":"0018-9219","issn":["0018-9219","1558-2256"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"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 IEEE","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8087102152","display_name":null,"funder_award_id":"442218748 (AUDI0NOMOUS)","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":88,"referenced_works":["https://openalex.org/W1929763453","https://openalex.org/W1970491336","https://openalex.org/W1988484949","https://openalex.org/W2044222806","https://openalex.org/W2052666245","https://openalex.org/W2103235956","https://openalex.org/W2108598243","https://openalex.org/W2127589108","https://openalex.org/W2176625348","https://openalex.org/W2194775991","https://openalex.org/W2399733683","https://openalex.org/W2566935005","https://openalex.org/W2593116425","https://openalex.org/W2612464443","https://openalex.org/W2617721296","https://openalex.org/W2759822254","https://openalex.org/W2763188033","https://openalex.org/W2810934215","https://openalex.org/W2897042519","https://openalex.org/W2898268964","https://openalex.org/W2900315145","https://openalex.org/W2936044260","https://openalex.org/W2956824775","https://openalex.org/W2959539607","https://openalex.org/W2963859210","https://openalex.org/W2982294822","https://openalex.org/W2982428733","https://openalex.org/W3015591594","https://openalex.org/W3021261768","https://openalex.org/W3021910945","https://openalex.org/W3034368386","https://openalex.org/W3041133507","https://openalex.org/W3044495139","https://openalex.org/W3085615212","https://openalex.org/W3094550259","https://openalex.org/W3138521398","https://openalex.org/W3161541317","https://openalex.org/W3161663055","https://openalex.org/W3162331882","https://openalex.org/W3162999565","https://openalex.org/W3174699664","https://openalex.org/W3178592608","https://openalex.org/W3185499768","https://openalex.org/W3196974791","https://openalex.org/W3197097128","https://openalex.org/W3197580070","https://openalex.org/W3206494219","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3212060048","https://openalex.org/W3215615641","https://openalex.org/W4205689591","https://openalex.org/W4210913346","https://openalex.org/W4221167652","https://openalex.org/W4226051760","https://openalex.org/W4233392025","https://openalex.org/W4256604311","https://openalex.org/W4310873011","https://openalex.org/W4311137818","https://openalex.org/W4312097006","https://openalex.org/W4312636570","https://openalex.org/W4313014461","https://openalex.org/W4361994820","https://openalex.org/W4372260217","https://openalex.org/W4372260310","https://openalex.org/W4372266552","https://openalex.org/W4381249885","https://openalex.org/W4385572634","https://openalex.org/W4385807453","https://openalex.org/W4385822467","https://openalex.org/W4389265800","https://openalex.org/W4391021627","https://openalex.org/W4392903210","https://openalex.org/W4392904037","https://openalex.org/W4392909683","https://openalex.org/W4393241166","https://openalex.org/W4400033239","https://openalex.org/W4400949264","https://openalex.org/W4402669724","https://openalex.org/W4402670262","https://openalex.org/W4403196715","https://openalex.org/W4404356490","https://openalex.org/W4404609584","https://openalex.org/W4404740148","https://openalex.org/W4404782964","https://openalex.org/W4404783473","https://openalex.org/W4406208390","https://openalex.org/W4412431720"],"related_works":["https://openalex.org/W2381393187","https://openalex.org/W2332779545","https://openalex.org/W2358060160","https://openalex.org/W2035483685","https://openalex.org/W1969764885","https://openalex.org/W596947562","https://openalex.org/W2793937822","https://openalex.org/W2790817834","https://openalex.org/W3196817267","https://openalex.org/W1976600725"],"abstract_inverted_index":{"Foundation":[0],"models":[1,121],"(FMs)":[2],"are":[3],"increasingly":[4],"spearheading":[5],"recent":[6],"advances":[7],"on":[8],"a":[9,44,78],"variety":[10],"of":[11,18,23,80,98],"tasks":[12,42,129],"that":[13,118,130],"fall":[14],"under":[15],"the":[16,21,37,47,56,71,91,114,131],"purview":[17],"computer":[19],"audition\u2014i.e.,":[20],"use":[22],"machines":[24],"to":[25,39,49,77,83],"understand":[26],"sounds.":[27],"They":[28],"feature":[29],"several":[30],"advantages":[31],"over":[32],"traditional":[33,106],"pipelines:":[34],"among":[35],"others,":[36],"ability":[38],"consolidate":[40],"multiple":[41,128],"in":[43,70],"single":[45],"model,":[46],"option":[48],"leverage":[50],"knowledge":[51],"from":[52,105],"other":[53],"modalities,":[54],"and":[55,74,122],"readily":[57],"available":[58],"interaction":[59],"with":[60],"human":[61],"users.":[62],"Naturally,":[63],"these":[64],"promises":[65],"have":[66,75],"created":[67],"substantial":[68],"excitement":[69],"audio":[72,100,132],"community":[73,133],"led":[76],"wave":[79],"early":[81],"attempts":[82],"build":[84],"new,":[85],"generalpurpose":[86],"FMs":[87],"for":[88],"audio.":[89],"In":[90],"present":[92],"contribution,":[93],"we":[94],"give":[95],"an":[96],"overview":[97],"computational":[99],"analysis":[101],"as":[102],"it":[103],"transitions":[104],"pipelines":[107],"toward":[108],"auditory":[109],"FMs.":[110],"Our":[111],"work":[112],"highlights":[113],"key":[115],"operating":[116],"principles":[117],"underpin":[119],"those":[120],"showcases":[123],"how":[124],"they":[125],"can":[126],"accommodate":[127],"previously":[134],"tackled":[135],"separately.":[136]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}