{"id":"https://openalex.org/W4406461852","doi":"https://doi.org/10.1109/slt61566.2024.10832254","title":"Measuring Sound Symbolism In Audio-Visual Models","display_name":"Measuring Sound Symbolism In Audio-Visual Models","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461852","doi":"https://doi.org/10.1109/slt61566.2024.10832254"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832254","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832254","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","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/A5114400193","display_name":"Wei-Cheng Tseng","orcid":null},"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":"Wei-Cheng Tseng","raw_affiliation_strings":["The University of Texas at Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053466746","display_name":"Yi-Jen Shih","orcid":"https://orcid.org/0000-0003-3481-3117"},"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":"Yi-Jen Shih","raw_affiliation_strings":["The University of Texas at Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004717608","display_name":"David Harwath","orcid":"https://orcid.org/0000-0003-0206-0253"},"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":"David Harwath","raw_affiliation_strings":["The University of Texas at Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008715111","display_name":"Raymond J. Mooney","orcid":"https://orcid.org/0000-0002-4504-0490"},"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":"Raymond Mooney","raw_affiliation_strings":["The University of Texas at Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.32079329,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1165","last_page":"1172"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9976000189781189,"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":0.9976000189781189,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9761999845504761,"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"}},{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":0.9390000104904175,"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/computer-science","display_name":"Computer science","score":0.6949238777160645},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.618633508682251},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.6181886196136475},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4049203395843506},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.24972662329673767},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.22900152206420898}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6949238777160645},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.618633508682251},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.6181886196136475},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4049203395843506},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.24972662329673767},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.22900152206420898},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832254","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832254","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","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":77,"referenced_works":["https://openalex.org/W104216173","https://openalex.org/W625960733","https://openalex.org/W1787224781","https://openalex.org/W1849277567","https://openalex.org/W1915485278","https://openalex.org/W1923184257","https://openalex.org/W1976353778","https://openalex.org/W2007697612","https://openalex.org/W2010523604","https://openalex.org/W2019649178","https://openalex.org/W2098586765","https://openalex.org/W2099869405","https://openalex.org/W2140987075","https://openalex.org/W2397955720","https://openalex.org/W2520627926","https://openalex.org/W2556930864","https://openalex.org/W2593116425","https://openalex.org/W2594633041","https://openalex.org/W2619383789","https://openalex.org/W2793374096","https://openalex.org/W2842511635","https://openalex.org/W2891205112","https://openalex.org/W2892341857","https://openalex.org/W2943363452","https://openalex.org/W2962862718","https://openalex.org/W2963902314","https://openalex.org/W2981945307","https://openalex.org/W3136021864","https://openalex.org/W3140854437","https://openalex.org/W3154807520","https://openalex.org/W3166396011","https://openalex.org/W3174311593","https://openalex.org/W3192926155","https://openalex.org/W3200287550","https://openalex.org/W3205786327","https://openalex.org/W3211858612","https://openalex.org/W3213472242","https://openalex.org/W4221153068","https://openalex.org/W4224875474","https://openalex.org/W4226182655","https://openalex.org/W4226380987","https://openalex.org/W4229494842","https://openalex.org/W4256262456","https://openalex.org/W4288351520","https://openalex.org/W4297808394","https://openalex.org/W4297950672","https://openalex.org/W4306814790","https://openalex.org/W4311731188","https://openalex.org/W4312261477","https://openalex.org/W4313156423","https://openalex.org/W4319862477","https://openalex.org/W4320086272","https://openalex.org/W4322766928","https://openalex.org/W4385572747","https://openalex.org/W4386071707","https://openalex.org/W4387964166","https://openalex.org/W4389115564","https://openalex.org/W4391021513","https://openalex.org/W4392902762","https://openalex.org/W4392910434","https://openalex.org/W6632119767","https://openalex.org/W6639896569","https://openalex.org/W6713064302","https://openalex.org/W6729977899","https://openalex.org/W6734194636","https://openalex.org/W6754420807","https://openalex.org/W6757635932","https://openalex.org/W6791353385","https://openalex.org/W6810168380","https://openalex.org/W6811013733","https://openalex.org/W6843825870","https://openalex.org/W6845527703","https://openalex.org/W6845577938","https://openalex.org/W6846678071","https://openalex.org/W6847495150","https://openalex.org/W6857180757","https://openalex.org/W6858202640"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W3137890128"],"abstract_inverted_index":{"Audio-visual":[0],"pre-trained":[1,20],"models":[2,22,53,80,90],"have":[3],"gained":[4],"substantial":[5],"attention":[6],"recently":[7],"and":[8,28,47,50,72,106],"demonstrated":[9],"superior":[10],"performance":[11],"on":[12,82],"various":[13],"audio-visual":[14,21],"tasks.":[15],"This":[16],"study":[17],"investigates":[18],"whether":[19],"demonstrate":[23],"non-arbitrary":[24],"associations":[25],"between":[26,68],"sounds":[27],"visual":[29],"representations-known":[30],"as":[31],"sound":[32,76],"symbolism-which":[33],"is":[34],"also":[35],"observed":[36],"in":[37,58,79],"humans.":[38],"We":[39],"developed":[40],"a":[41,55,59,65],"specialized":[42],"dataset":[43],"with":[44],"synthesized":[45],"images":[46],"audio":[48],"samples":[49],"assessed":[51],"these":[52],"using":[54],"non-parametric":[56],"approach":[57],"zero-shot":[60],"setting.":[61],"Our":[62],"findings":[63],"reveal":[64],"significant":[66],"correlation":[67],"the":[69],"models\u2019":[70],"outputs":[71],"established":[73],"patterns":[74],"of":[75],"symbolism,":[77],"particularly":[78],"trained":[81],"speech":[83],"data.":[84],"These":[85],"results":[86],"suggest":[87],"that":[88],"such":[89],"can":[91],"capture":[92],"sound-meaning":[93],"connections":[94],"akin":[95],"to":[96],"human":[97],"language":[98],"processing,":[99],"providing":[100],"insights":[101],"into":[102],"both":[103],"cognitive":[104],"architectures":[105],"machine":[107],"learning":[108],"strategies.":[109]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}