{"id":"https://openalex.org/W7166806903","doi":"https://doi.org/10.18653/v1/2026.acl-long.1038","title":"Omni-Embed-Audio: Leveraging Multimodal LLMs for Robust Audio-Text Retrieval","display_name":"Omni-Embed-Audio: Leveraging Multimodal LLMs for Robust Audio-Text Retrieval","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166806903","doi":"https://doi.org/10.18653/v1/2026.acl-long.1038"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.acl-long.1038","doi":"https://doi.org/10.18653/v1/2026.acl-long.1038","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1038","pdf_url":"https://aclanthology.org/2026.acl-long.1038.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2026.acl-long.1038.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130382021","display_name":"Haejun Yoo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I148751991","display_name":"Sogang University","ror":"https://ror.org/056tn4839","country_code":"KR","type":"education","lineage":["https://openalex.org/I148751991"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"HaeJun Yoo","raw_affiliation_strings":["Sogang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sogang University","institution_ids":["https://openalex.org/I148751991"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134115286","display_name":"Yongseop Shin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I148751991","display_name":"Sogang University","ror":"https://ror.org/056tn4839","country_code":"KR","type":"education","lineage":["https://openalex.org/I148751991"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yongseop Shin","raw_affiliation_strings":["Sogang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sogang University","institution_ids":["https://openalex.org/I148751991"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134121843","display_name":"Insung Lee","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I148751991","display_name":"Sogang University","ror":"https://ror.org/056tn4839","country_code":"KR","type":"education","lineage":["https://openalex.org/I148751991"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Insung Lee","raw_affiliation_strings":["Sogang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sogang University","institution_ids":["https://openalex.org/I148751991"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130332621","display_name":"Myoung-Wan Koo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I148751991","display_name":"Sogang University","ror":"https://ror.org/056tn4839","country_code":"KR","type":"education","lineage":["https://openalex.org/I148751991"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Myoung-Wan Koo","raw_affiliation_strings":["Sogang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sogang University","institution_ids":["https://openalex.org/I148751991"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050902284","display_name":"Du-Seong Chang","orcid":"https://orcid.org/0000-0001-6692-962X","observed_orcids":["https://orcid.org/0000-0001-6692-962X"]},"institutions":[{"id":"https://openalex.org/I148751991","display_name":"Sogang University","ror":"https://ror.org/056tn4839","country_code":"KR","type":"education","lineage":["https://openalex.org/I148751991"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Du-Seong Chang","raw_affiliation_strings":["Sogang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sogang University","institution_ids":["https://openalex.org/I148751991"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I148751991"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.49016068,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"22664","last_page":"22680"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9589999914169312,"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":0.9589999914169312,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.01899999938905239,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.009600000455975533,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/audio-text-retrieval","display_name":"audio-text retrieval","score":0.9929999709129333},{"id":"https://openalex.org/keywords/multimodal-large-language-models","display_name":"multimodal large language models","score":0.75},{"id":"https://openalex.org/keywords/clap","display_name":"CLAP","score":0.8140000104904175},{"id":"https://openalex.org/keywords/hard-negative-mining","display_name":"hard negative mining","score":0.953000009059906},{"id":"https://openalex.org/keywords/retrieval-robustness","display_name":"retrieval robustness","score":0.6740000247955322},{"id":"https://openalex.org/keywords/audio-understanding","display_name":"audio understanding","score":0.4320000112056732}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.592199981212616},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4032000005245209},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3068000078201294},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.24959999322891235},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.24310000240802765},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.24120000004768372},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2387000024318695},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.23180000483989716},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2304999977350235},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.22679999470710754}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.1038","doi":"https://doi.org/10.18653/v1/2026.acl-long.1038","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1038","pdf_url":"https://aclanthology.org/2026.acl-long.1038.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.1038","doi":"https://doi.org/10.18653/v1/2026.acl-long.1038","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1038","pdf_url":"https://aclanthology.org/2026.acl-long.1038.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G2452400178","display_name":null,"funder_award_id":"RS-2025-25441313","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"}],"funders":[{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166806903.pdf","grobid_xml":"https://content.openalex.org/works/W7166806903.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7131126719","https://openalex.org/W3158978276","https://openalex.org/W4210913346","https://openalex.org/W7157313371","https://openalex.org/W7160434960","https://openalex.org/W4304892597","https://openalex.org/W4385749716","https://openalex.org/W4415821098","https://openalex.org/W4385822467","https://openalex.org/W4404519040"],"abstract_inverted_index":{"Audio-text":[0],"retrieval":[1,34,108,123],"systems":[2],"based":[3],"on":[4,12,19,97],"Contrastive":[5],"Language-Audio":[6],"Pretraining":[7],"(CLAP)":[8],"achieve":[9],"strong":[10],"performance":[11,109],"traditional":[13],"benchmarks;":[14],"however,":[15],"these":[16],"benchmarks":[17],"rely":[18],"caption-style":[20],"queries":[21],"that":[22,103,139],"differ":[23],"substantially":[24,129],"from":[25],"real-world":[26],"search":[27,63],"behavior,":[28],"limiting":[29],"their":[30],"assessment":[31],"of":[32,146],"practical":[33],"robustness.We":[35],"present":[36],"Omni-Embed-Audio":[37],"(OEA),":[38],"a":[39,78],"retrievaloriented":[40],"encoder":[41],"leveraging":[42],"multimodal":[43],"LLMs":[44],"with":[45],"native":[46],"audio":[47],"understanding.To":[48],"systematically":[49],"evaluate":[50],"robustness":[51],"beyond":[52],"captionstyle":[53],"queries,":[54,75],"we":[55,76],"introduce":[56],"User-Intent":[57],"Queries":[58],"(UIQs)-five":[59],"formulations":[60],"reflecting":[61],"natural":[62],"behaviors:":[64],"questions,":[65],"commands,":[66],"keyword":[67],"tags,":[68],"paraphrases,":[69],"and":[70,83,100,127],"exclusion-based":[71],"negative":[72,74,80,132],"queries.For":[73],"develop":[77],"hard":[79,131],"mining":[81],"pipeline":[82],"propose":[84],"discrimination":[85,133],"metrics":[86],"(HNSR,":[87],"TFR)":[88],"assessing":[89],"models'":[90],"ability":[91],"to":[92,110],"suppress":[93],"acoustically":[94],"similar":[95],"distractors.Experiments":[96],"AudioCaps,":[98],"Clotho,":[99],"MECAT":[101],"show":[102],"OEA":[104],"achieves":[105],"comparable":[106],"text-to-audio":[107],"state-of-the-art":[111],"M2D-CLAP,":[112],"while":[113],"demonstrating":[114],"clear":[115],"advantages":[116],"in":[117],"two":[118],"critical":[119],"areas:(1)":[120],"dominant":[121],"text-to-text":[122],"(+22%":[124],"relative":[125,136],"improvement),":[126],"(2)":[128],"superior":[130,143],"(+4.3%pHNSR@10,":[134],"+34.7%":[135],"TFR@10),":[137],"revealing":[138],"LLM":[140],"backbones":[141],"provide":[142],"semantic":[144],"understanding":[145],"complex":[147],"queries.":[148]},"counts_by_year":[],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2026-07-02T00:00:00"}