{"id":"https://openalex.org/W4408352226","doi":"https://doi.org/10.1109/icassp49660.2025.10888245","title":"On Class Separability Pitfalls In Audio-Text Contrastive Zero-Shot Learning","display_name":"On Class Separability Pitfalls In Audio-Text Contrastive Zero-Shot Learning","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352226","doi":"https://doi.org/10.1109/icassp49660.2025.10888245"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888245","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888245","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/A5057729011","display_name":"Tiago Fernandes Tavares","orcid":"https://orcid.org/0000-0002-9104-613X"},"institutions":[{"id":"https://openalex.org/I52977244","display_name":"Insper","ror":"https://ror.org/02nmavx05","country_code":"BR","type":"education","lineage":["https://openalex.org/I52977244"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Tiago Fernandes Tavares","raw_affiliation_strings":["INSPER São Paulo,São Paulo,Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INSPER São Paulo,São Paulo,Brazil","institution_ids":["https://openalex.org/I52977244"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009630456","display_name":"F\u00e1bio J. Ayres","orcid":"https://orcid.org/0009-0000-6821-4687"},"institutions":[{"id":"https://openalex.org/I52977244","display_name":"Insper","ror":"https://ror.org/02nmavx05","country_code":"BR","type":"education","lineage":["https://openalex.org/I52977244"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Fabio Jos\u00e9 Ayres","raw_affiliation_strings":["INSPER São Paulo,São Paulo,Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INSPER São Paulo,São Paulo,Brazil","institution_ids":["https://openalex.org/I52977244"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102709539","display_name":"Zhepei Wang","orcid":"https://orcid.org/0000-0001-7845-5273"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhepei Wang","raw_affiliation_strings":["University of Illinois at Urbana-Champaign,Urbana,IL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign,Urbana,IL","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038903729","display_name":"Paris Smaragdis","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paris Smaragdis","raw_affiliation_strings":["University of Illinois at Urbana-Champaign,Urbana,IL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign,Urbana,IL","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.9945,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.95238533,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":96},"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/T11609","display_name":"Geophysical Methods and Applications","score":0.902899980545044,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11609","display_name":"Geophysical Methods and Applications","score":0.902899980545044,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7077257633209229},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.6381542086601257},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.6248867511749268},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.5504754185676575},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.53568035364151},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4248090386390686},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3661883473396301},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.14089170098304749}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7077257633209229},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6381542086601257},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.6248867511749268},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5504754185676575},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.53568035364151},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4248090386390686},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3661883473396301},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.14089170098304749},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888245","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888245","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":21,"referenced_works":["https://openalex.org/W1987971958","https://openalex.org/W2052666245","https://openalex.org/W2593116425","https://openalex.org/W2596142952","https://openalex.org/W2963341956","https://openalex.org/W2998351764","https://openalex.org/W3015591594","https://openalex.org/W3094550259","https://openalex.org/W3138521398","https://openalex.org/W3143107425","https://openalex.org/W3162331882","https://openalex.org/W4205689591","https://openalex.org/W4285787895","https://openalex.org/W4312763854","https://openalex.org/W4372260310","https://openalex.org/W4372266552","https://openalex.org/W4385822467","https://openalex.org/W6765174816","https://openalex.org/W6770649906","https://openalex.org/W6791353385","https://openalex.org/W6809885388"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W4298312966","https://openalex.org/W2325697621"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,32,39,80,128],"audio-text":[3],"cross-modal":[4,30,87,130],"contrastive":[5],"learning":[6,79,94,109],"have":[7],"shown":[8],"its":[9],"potential":[10],"towards":[11],"zero-shot":[12,93,108],"learning.":[13],"One":[14],"possibility":[15],"for":[16,60],"this":[17,97],"is":[18,111],"by":[19,69],"projecting":[20],"item":[21,34],"embeddings":[22],"from":[23,76,83,91,116,136],"pre-trained":[24],"backbone":[25,52],"neural":[26],"networks":[27],"into":[28],"a":[29,46,56,102],"space":[31],"which":[33,73],"similarity":[35],"can":[36,66,74],"be":[37,67],"calculated":[38],"either":[40],"domain.":[41],"This":[42],"process":[43],"relies":[44],"on":[45,55],"strong":[47],"unimodal":[48],"pre-training":[49,81],"of":[50,105],"the":[51,61,86,92,106,117,129],"networks,":[53],"and":[54,119,132],"data-intensive":[57],"training":[58,85],"task":[59],"projectors.":[62],"These":[63],"two":[64],"processes":[65],"biased":[68],"unintentional":[70],"data":[71],"leakage,":[72],"arise":[75],"using":[77,89],"supervised":[78],"or":[82],"inadvertently":[84],"projection":[88],"labels":[90],"evaluation.":[95],"In":[96],"study,":[98],"we":[99],"show":[100],"that":[101,122],"significant":[103],"part":[104],"measured":[107],"accuracy":[110],"due":[112],"to":[113,139],"strengths":[114],"inherited":[115],"audio":[118],"text":[120],"backbones,":[121],"is,":[123],"they":[124],"are":[125,133],"not":[126,134],"learned":[127],"domain":[131],"transferred":[135],"one":[137],"modality":[138],"another.":[140]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}