{"id":"https://openalex.org/W4406610179","doi":"https://doi.org/10.1109/lsp.2025.3532218","title":"Improving Audio Explanations Using Audio Language Models","display_name":"Improving Audio Explanations Using Audio Language Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4406610179","doi":"https://doi.org/10.1109/lsp.2025.3532218"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2025.3532218","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3532218","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069525898","display_name":"Alican Akman","orcid":"https://orcid.org/0000-0002-8010-6897"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Alican Akman","raw_affiliation_strings":["GLAM, Department of Computing, Imperial College London, London, U.K"],"raw_orcid":"https://orcid.org/0000-0002-8010-6897","affiliations":[{"raw_affiliation_string":"GLAM, Department of Computing, Imperial College London, London, U.K","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114245462","display_name":"Qiyang Sun","orcid":"https://orcid.org/0009-0001-9228-4543"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Qiyang Sun","raw_affiliation_strings":["GLAM, Department of Computing, Imperial College London, London, U.K"],"raw_orcid":"https://orcid.org/0009-0001-9228-4543","affiliations":[{"raw_affiliation_string":"GLAM, Department of Computing, Imperial College London, London, U.K","institution_ids":["https://openalex.org/I47508984"]}]},{"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/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Bj\u00f6rn W. Schuller","raw_affiliation_strings":["GLAM, Department of Computing, Imperial College London, London, U.K"],"raw_orcid":"https://orcid.org/0000-0002-6478-8699","affiliations":[{"raw_affiliation_string":"GLAM, Department of Computing, Imperial College London, London, U.K","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I47508984"],"apc_list":null,"apc_paid":null,"fwci":5.1658,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.94474802,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"32","issue":null,"first_page":"741","last_page":"745"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9884999990463257,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9884999990463257,"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":0.9696999788284302,"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/T11309","display_name":"Music and Audio Processing","score":0.9696000218391418,"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/computer-science","display_name":"Computer science","score":0.7467786073684692},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.532680094242096},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.5301141738891602},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5282936096191406},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.4962766766548157},{"id":"https://openalex.org/keywords/digital-audio","display_name":"Digital audio","score":0.47070667147636414},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4523618221282959},{"id":"https://openalex.org/keywords/digital-audio-broadcasting","display_name":"Digital audio broadcasting","score":0.4458228647708893},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.42310231924057007},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.29933077096939087},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.2334924340248108},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08903005719184875}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7467786073684692},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.532680094242096},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.5301141738891602},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5282936096191406},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.4962766766548157},{"id":"https://openalex.org/C87687168","wikidata":"https://www.wikidata.org/wiki/Q173114","display_name":"Digital audio","level":4,"score":0.47070667147636414},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4523618221282959},{"id":"https://openalex.org/C2779106878","wikidata":"https://www.wikidata.org/wiki/Q1257510","display_name":"Digital audio broadcasting","level":2,"score":0.4458228647708893},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.42310231924057007},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.29933077096939087},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.2334924340248108},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08903005719184875}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lsp.2025.3532218","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3532218","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},{"id":"pmh:oai:mediatum.ub.tum.de:node/1795821","is_oa":false,"landing_page_url":"https://mediatum.ub.tum.de/1795821","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1787224781","https://openalex.org/W2516809705","https://openalex.org/W2770398803","https://openalex.org/W2797583228","https://openalex.org/W2963749936","https://openalex.org/W3109943296","https://openalex.org/W3196974791","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3211224152","https://openalex.org/W3215615641","https://openalex.org/W4251179700","https://openalex.org/W4294975502","https://openalex.org/W4307323391","https://openalex.org/W4377010126","https://openalex.org/W4384918448","https://openalex.org/W4387595589","https://openalex.org/W4392172995","https://openalex.org/W4402669711","https://openalex.org/W4403364412","https://openalex.org/W6680012447","https://openalex.org/W6728458142","https://openalex.org/W6734194636","https://openalex.org/W6746084291","https://openalex.org/W6750391026","https://openalex.org/W6750665317","https://openalex.org/W6752170072","https://openalex.org/W6769196770","https://openalex.org/W6778883912","https://openalex.org/W6780218876","https://openalex.org/W6786585944","https://openalex.org/W6803378298","https://openalex.org/W6810185292","https://openalex.org/W6845479124","https://openalex.org/W6847363464","https://openalex.org/W6853096648","https://openalex.org/W6853188576","https://openalex.org/W6854866820","https://openalex.org/W6873799666"],"related_works":["https://openalex.org/W2130109774","https://openalex.org/W1979717040","https://openalex.org/W2363106653","https://openalex.org/W296599067","https://openalex.org/W2797066576","https://openalex.org/W1975359510","https://openalex.org/W1496727373","https://openalex.org/W2494591065","https://openalex.org/W1611900921","https://openalex.org/W1969715806"],"abstract_inverted_index":{"Foundation":[0],"models":[1,24,120],"are":[2],"widely":[3],"utilised":[4],"for":[5,92],"their":[6,38,60],"strong":[7],"representational":[8,78],"capabilities,":[9],"driven":[10],"by":[11,48],"training":[12],"on":[13,59,62,142],"extensive":[14,140],"datasets":[15],"with":[16,125],"self-supervised":[17],"learning.":[18],"The":[19],"increasing":[20],"complexity":[21],"of":[22,28,37,108,117,134],"these":[23],"highlights":[25],"the":[26,63,71,76,114,135],"importance":[27,50],"interpretability":[29,43],"to":[30,51,100,121],"enhance":[31],"transparency":[32],"and":[33,148],"improve":[34],"human":[35],"understanding":[36,107],"decision-making":[39,137],"processes.":[40],"Most":[41],"existing":[42],"methods":[44],"explain":[45],"model":[46,109],"behaviour":[47],"attributing":[49],"individual":[52],"data":[53],"elements":[54],"across":[55],"different":[56],"layers,":[57],"based":[58],"influence":[61],"final":[64],"prediction.":[65],"These":[66],"approaches":[67],"often":[68],"emphasise":[69],"only":[70],"most":[72],"relevant":[73],"features,":[74],"overlooking":[75],"broader":[77],"space,":[79],"removing":[80],"less":[81],"important":[82],"features.":[83],"In":[84],"this":[85],"study,":[86],"we":[87],"propose":[88],"a":[89,104,130],"novel":[90],"framework":[91,112],"explanation":[93],"generation":[94],"that":[95],"serves":[96],"as":[97],"an":[98],"alternative":[99],"feature":[101],"removal,":[102],"offering":[103],"more":[105,131],"comprehensive":[106],"behaviour.":[110],"Our":[111],"leverages":[113],"generative":[115],"abilities":[116],"audio":[118,160],"language":[119],"replace":[122],"removed":[123],"features":[124],"contextually":[126],"appropriate":[127],"alternatives,":[128],"providing":[129],"complete":[132],"view":[133],"model's":[136],"process.":[138],"Through":[139],"evaluations":[141],"standard":[143],"benchmarks,":[144],"including":[145],"keyword":[146],"spotting":[147],"speech":[149],"emotion":[150],"recognition,":[151],"our":[152],"approach":[153],"demonstrates":[154],"its":[155],"effectiveness":[156],"in":[157],"generating":[158],"high-quality":[159],"explanations.":[161]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-17T09:13:05.818461","created_date":"2025-10-10T00:00:00"}