{"id":"https://openalex.org/W4416251241","doi":"https://doi.org/10.1109/ijcnn64981.2025.11229318","title":"Transformation of audio embeddings into interpretable, concept-based representations","display_name":"Transformation of audio embeddings into interpretable, concept-based representations","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416251241","doi":"https://doi.org/10.1109/ijcnn64981.2025.11229318"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11229318","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11229318","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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/A5063874126","display_name":"Alice Zhang","orcid":"https://orcid.org/0009-0006-0148-095X"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alice Zhang","raw_affiliation_strings":["Univ. of Texas at Austin,Dept. of Electrical and Computer Engineering,Austin,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. of Texas at Austin,Dept. of Electrical and Computer Engineering,Austin,USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025977484","display_name":"Edison Thomaz","orcid":"https://orcid.org/0000-0001-8188-0457"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Edison Thomaz","raw_affiliation_strings":["Univ. of Texas at Austin,Dept. of Electrical and Computer Engineering,Austin,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. of Texas at Austin,Dept. of Electrical and Computer Engineering,Austin,USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110491600","display_name":"Lie Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210093996","display_name":"Dolby (United States)","ror":"https://ror.org/01eyenr26","country_code":"US","type":"company","lineage":["https://openalex.org/I4210093996"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lie Lu","raw_affiliation_strings":["Dolby Laboratories,San Francisco,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dolby Laboratories,San Francisco,USA","institution_ids":["https://openalex.org/I4210093996"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.42173594,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.40470001101493835,"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":0.40470001101493835,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.19599999487400055,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.06120000034570694,"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/interpretability","display_name":"Interpretability","score":0.8967999815940857},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6215999722480774},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.4839000105857849},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.37549999356269836},{"id":"https://openalex.org/keywords/downstream","display_name":"Downstream (manufacturing)","score":0.3596000075340271},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.34279999136924744},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.31279999017715454}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.8967999815940857},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7530999779701233},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6215999722480774},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5264999866485596},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4885999858379364},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.4839000105857849},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.37549999356269836},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.3596000075340271},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.34279999136924744},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3382999897003174},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.31279999017715454},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3095000088214874},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.30000001192092896},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2930999994277954},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2842999994754791},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.2815000116825104},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C87687168","wikidata":"https://www.wikidata.org/wiki/Q173114","display_name":"Digital audio","level":4,"score":0.2596000134944916},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2554999887943268},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.2538999915122986}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11229318","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11229318","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2038484192","https://openalex.org/W2052666245","https://openalex.org/W2493343568","https://openalex.org/W2516809705","https://openalex.org/W2593116425","https://openalex.org/W2938440247","https://openalex.org/W3015591594","https://openalex.org/W3094550259","https://openalex.org/W3127493833","https://openalex.org/W3176445421","https://openalex.org/W4205689591","https://openalex.org/W4225299287","https://openalex.org/W4226442948","https://openalex.org/W4312715377","https://openalex.org/W4372260310","https://openalex.org/W4372266552","https://openalex.org/W4390190587","https://openalex.org/W4392903801","https://openalex.org/W4400033239","https://openalex.org/W4401042934","https://openalex.org/W4402754178","https://openalex.org/W4415796756"],"related_works":[],"abstract_inverted_index":{"Advancements":[0],"in":[1,28],"audio":[2,11,31,42,58,98,132],"neural":[3,47],"networks":[4,48],"have":[5],"established":[6],"state-of-the-art":[7],"results":[8],"on":[9,100,119],"downstream":[10,101,120],"tasks.":[12,121],"However,":[13],"the":[14,25,38,88,94,111],"black-box":[15],"structure":[16],"of":[17,41,96,131],"these":[18,46],"models":[19],"makes":[20],"it":[21],"difficult":[22],"to":[23,71],"interpret":[24],"information":[26],"encoded":[27],"their":[29,117],"internal":[30],"representations.":[32],"In":[33],"this":[34],"work,":[35],"we":[36,107,123],"explore":[37],"semantic":[39,80],"interpretability":[40,130],"embeddings":[43,74,99],"extracted":[44],"from":[45],"by":[49],"leveraging":[50],"CLAP,":[51],"a":[52,62,68],"contrastive":[53],"learning":[54],"model":[55],"that":[56,87,109],"brings":[57],"and":[59,83],"text":[60],"into":[61,75],"shared":[63],"embedding":[64],"space.":[65],"We":[66],"implement":[67],"post-hoc":[69],"method":[70],"transform":[72],"CLAP":[73],"concept-based,":[76],"sparse":[77],"representations":[78,90,113],"with":[79],"interpretability.":[81,105],"Qualitative":[82],"quantitative":[84],"evaluations":[85],"show":[86],"concept-based":[89,112,129],"outperform":[91],"or":[92],"match":[93],"performance":[95,118],"original":[97],"tasks":[102],"while":[103],"providing":[104],"Additionally,":[106],"demonstrate":[108],"fine-tuning":[110],"can":[114],"further":[115],"improve":[116],"Lastly,":[122],"publish":[124],"three":[125],"audio-specific":[126],"vocabularies":[127],"for":[128],"embeddings.":[133]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-14T00:00:00"}