{"id":"https://openalex.org/W4412945667","doi":"https://doi.org/10.18653/v1/2025.acl-long.428","title":"Mind the Gap: Static and Interactive Evaluations of Large Audio Models","display_name":"Mind the Gap: Static and Interactive Evaluations of Large Audio Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412945667","doi":"https://doi.org/10.18653/v1/2025.acl-long.428"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.428","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.428","pdf_url":"https://aclanthology.org/2025.acl-long.428.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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.428.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022683477","display_name":"Minzhi Li","orcid":"https://orcid.org/0000-0002-1013-8930"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Minzhi Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109972562","display_name":"William A. Held","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"William Held","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067054671","display_name":"Michael J. Ryan","orcid":"https://orcid.org/0000-0002-6381-9545"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael J. Ryan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021237405","display_name":"Kunat Pipatanakul","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kunat Pipatanakul","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024447363","display_name":"Potsawee Manakul","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Potsawee Manakul","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Hao Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Zhu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5089413311","display_name":"Diyi Yang","orcid":"https://orcid.org/0000-0003-1220-3983"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Diyi Yang","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":"8749","last_page":"8766"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.96670001745224,"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"}},"topics":[{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.96670001745224,"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/T11309","display_name":"Music and Audio Processing","score":0.9466999769210815,"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/computer-science","display_name":"Computer science","score":0.7491899132728577},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.42220380902290344},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.4143868386745453},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3755165934562683},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.36928242444992065},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.34447747468948364},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.21889755129814148},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.163395494222641}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7491899132728577},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.42220380902290344},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.4143868386745453},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3755165934562683},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.36928242444992065},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.34447747468948364},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.21889755129814148},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.163395494222641}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.428","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.428","pdf_url":"https://aclanthology.org/2025.acl-long.428.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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.428","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.428","pdf_url":"https://aclanthology.org/2025.acl-long.428.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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412945667.pdf","grobid_xml":"https://content.openalex.org/works/W4412945667.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2098934641","https://openalex.org/W3135871143","https://openalex.org/W4382560817","https://openalex.org/W2347715673","https://openalex.org/W2405875744","https://openalex.org/W296599067","https://openalex.org/W2020966186","https://openalex.org/W2119339729","https://openalex.org/W4387698063","https://openalex.org/W27741130"],"abstract_inverted_index":{"Minzhi":[0],"Li,":[1],"William":[2],"Held,":[3],"Michael":[4],"J.":[5],"Ryan,":[6],"Kunat":[7],"Pipatanakul,":[8],"Potsawee":[9],"Manakul,":[10],"Hao":[11],"Zhu,":[12],"Diyi":[13],"Yang.":[14],"Proceedings":[15],"of":[16,21],"the":[17,22],"63rd":[18],"Annual":[19],"Meeting":[20],"Association":[23],"for":[24],"Computational":[25],"Linguistics":[26],"(Volume":[27],"1:":[28],"Long":[29],"Papers).":[30],"2025.":[31]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}