{"id":"https://openalex.org/W4408354583","doi":"https://doi.org/10.1109/icassp49660.2025.10890370","title":"Audio Explanation Synthesis with Generative Foundation Models","display_name":"Audio Explanation Synthesis with Generative Foundation Models","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354583","doi":"https://doi.org/10.1109/icassp49660.2025.10890370"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890370","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890370","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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":["Imperial College,GLAM,London,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College,GLAM,London,UK","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":["Imperial College,GLAM,London,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College,GLAM,London,UK","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":["Imperial College,GLAM,London,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College,GLAM,London,UK","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":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.983299970626831,"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":0.983299970626831,"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":0.9235000014305115,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9053000211715698,"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/foundation","display_name":"Foundation (evidence)","score":0.6818472146987915},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6675295829772949},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6316484212875366},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2745800316333771},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.05131107568740845}],"concepts":[{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.6818472146987915},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6675295829772949},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6316484212875366},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2745800316333771},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.05131107568740845},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890370","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890370","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1787224781","https://openalex.org/W2963749936","https://openalex.org/W3015213852","https://openalex.org/W3144810982","https://openalex.org/W3148040514","https://openalex.org/W3206494219","https://openalex.org/W4220714107","https://openalex.org/W4294975502","https://openalex.org/W4307323391","https://openalex.org/W4387966251","https://openalex.org/W4391486587","https://openalex.org/W6639204139","https://openalex.org/W6680012447","https://openalex.org/W6687502627","https://openalex.org/W6703326205","https://openalex.org/W6726258750","https://openalex.org/W6728458142","https://openalex.org/W6734194636","https://openalex.org/W6736518430","https://openalex.org/W6746084291","https://openalex.org/W6750391026","https://openalex.org/W6750665317","https://openalex.org/W6752170072","https://openalex.org/W6753441104","https://openalex.org/W6763367618","https://openalex.org/W6769196770","https://openalex.org/W6769430237","https://openalex.org/W6777047548","https://openalex.org/W6786585944","https://openalex.org/W6792861227","https://openalex.org/W6796554684","https://openalex.org/W6803164887","https://openalex.org/W6852010021"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2381393187","https://openalex.org/W2332779545","https://openalex.org/W2380075625","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W2358060160"],"abstract_inverted_index":{"The":[0,98],"increasing":[1],"success":[2],"of":[3,67,78],"audio":[4,58,68,103,131],"foundation":[5,69],"models":[6,33,84],"across":[7],"various":[8],"tasks":[9],"has":[10],"led":[11],"to":[12,19,37,91],"a":[13,56],"growing":[14],"need":[15],"for":[16],"improved":[17],"interpretability":[18],"understand":[20],"their":[21,45],"intricate":[22],"decision-making":[23],"processes":[24],"better.":[25],"Existing":[26],"methods":[27],"primarily":[28],"focus":[29],"on":[30,44,47,63],"explaining":[31],"these":[32,83],"by":[34,85,105],"attributing":[35],"importance":[36],"elements":[38],"within":[39,82],"the":[40,48,64,74,79,107],"input":[41],"space":[42,81],"based":[43],"influence":[46],"final":[49],"decision.":[50],"In":[51],"this":[52,96],"paper,":[53],"we":[54],"introduce":[55],"novel":[57],"explanation":[59],"method":[60,72,99],"that":[61],"capitalises":[62],"generative":[65],"capacity":[66],"models.":[70],"Our":[71],"leverages":[73],"intrinsic":[75],"representational":[76],"power":[77],"embedding":[80],"integrating":[86],"established":[87],"feature":[88],"attribution":[89],"techniques":[90],"identify":[92],"significant":[93],"features":[94],"in":[95,129],"space.":[97],"then":[100],"generates":[101],"listenable":[102],"explanations":[104],"prioritising":[106],"most":[108],"important":[109],"features.":[110],"Through":[111],"rigorous":[112],"benchmarking":[113],"against":[114],"standard":[115],"datasets,":[116],"including":[117],"keyword":[118],"spotting":[119],"and":[120],"speech":[121],"emotion":[122],"recognition,":[123],"our":[124],"model":[125],"demonstrates":[126],"its":[127],"efficacy":[128],"producing":[130],"explanations.":[132]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}