{"id":"https://openalex.org/W7138176896","doi":"https://doi.org/10.18653/v1/2025.ijcnlp-short.7","title":"Seeing isn\u2019t Hearing: Benchmarking Vision Language Models at Interpreting Spectrograms","display_name":"Seeing isn\u2019t Hearing: Benchmarking Vision Language Models at Interpreting Spectrograms","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W7138176896","doi":"https://doi.org/10.18653/v1/2025.ijcnlp-short.7"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.ijcnlp-short.7","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.ijcnlp-short.7","pdf_url":"https://aclanthology.org/2025.ijcnlp-short.7.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.ijcnlp-short.7.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038302646","display_name":"Tyler Loakman","orcid":"https://orcid.org/0000-0001-5333-7780"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tyler Loakman","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129692756","display_name":"Joseph James","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Joseph James","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129704530","display_name":"Chenghua Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chenghua Lin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"79","last_page":"86"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11285","display_name":"Hearing Impairment and Communication","score":0.22920000553131104,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11285","display_name":"Hearing Impairment and Communication","score":0.22920000553131104,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.10589999705553055,"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/T13310","display_name":"Subtitles and Audiovisual Media","score":0.08959999680519104,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.5720999836921692},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.444599986076355},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3474999964237213},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3206000030040741},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.30799999833106995},{"id":"https://openalex.org/keywords/interpretation","display_name":"Interpretation (philosophy)","score":0.271699994802475}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.607200026512146},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.5720999836921692},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5339000225067139},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44749999046325684},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.444599986076355},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.42160001397132874},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3474999964237213},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3206000030040741},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3107999861240387},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.30799999833106995},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2791999876499176},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.271699994802475},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.2621999979019165},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.25369998812675476},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.2522999942302704}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.ijcnlp-short.7","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.ijcnlp-short.7","pdf_url":"https://aclanthology.org/2025.ijcnlp-short.7.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.ijcnlp-short.7","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.ijcnlp-short.7","pdf_url":"https://aclanthology.org/2025.ijcnlp-short.7.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138176896.pdf","grobid_xml":"https://content.openalex.org/works/W7138176896.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Tyler":[0],"Loakman,":[1],"Joseph":[2],"James,":[3],"Chenghua":[4],"Lin.":[5],"Proceedings":[6],"of":[7,21,25],"the":[8,18,22,26],"14th":[9],"International":[10],"Joint":[11],"Conference":[12,20],"on":[13],"Natural":[14],"Language":[15],"Processing":[16],"and":[17],"4th":[19],"Asia-Pacific":[23],"Chapter":[24],"Association":[27],"for":[28],"Computational":[29],"Linguistics.":[30],"2025.":[31]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}
