{"id":"https://openalex.org/W4415821098","doi":"https://doi.org/10.1109/access.2025.3628289","title":"Nanami: Hybrid Embedding With Voice Large Language Models for Audio Retrieval","display_name":"Nanami: Hybrid Embedding With Voice Large Language Models for Audio Retrieval","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4415821098","doi":"https://doi.org/10.1109/access.2025.3628289"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3628289","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3628289","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3628289","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Gaojun Hu","orcid":"https://orcid.org/0009-0000-4538-6195"},"institutions":[{"id":"https://openalex.org/I199305430","display_name":"Nantong University","ror":"https://ror.org/02afcvw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I199305430"]},{"id":"https://openalex.org/I4210086801","display_name":"Affiliated Hospital of Nantong University","ror":"https://ror.org/001rahr89","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210086801"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Gaojun Hu","raw_affiliation_strings":["The People’s Hospital of Danyang, Affiliated Danyang Hospital of Nantong University, Danyang, Jiangsu, China","The People’s Hospital of Danyang, Affiliated Danyang Hospital of Nantong University, Danyang, Jiangsu Province, China"],"raw_orcid":"https://orcid.org/0009-0000-4538-6195","affiliations":[{"raw_affiliation_string":"The People’s Hospital of Danyang, Affiliated Danyang Hospital of Nantong University, Danyang, Jiangsu, China","institution_ids":["https://openalex.org/I199305430","https://openalex.org/I4210086801"]},{"raw_affiliation_string":"The People’s Hospital of Danyang, Affiliated Danyang Hospital of Nantong University, Danyang, Jiangsu Province, China","institution_ids":["https://openalex.org/I199305430","https://openalex.org/I4210086801"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I199305430","https://openalex.org/I4210086801"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.32696491,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"13","issue":null,"first_page":"189713","last_page":"189724"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.7225000262260437,"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":0.7225000262260437,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.17820000648498535,"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/T10860","display_name":"Speech and Audio Processing","score":0.014299999922513962,"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/embedding","display_name":"Embedding","score":0.7035999894142151},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5299000144004822},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.5030999779701233},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4487000107765198},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.40880000591278076},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.40459999442100525},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.362199991941452},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.35740000009536743}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8820000290870667},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7035999894142151},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5504999756813049},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5299000144004822},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5227000117301941},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.5030999779701233},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4487000107765198},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.40880000591278076},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.40459999442100525},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.362199991941452},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3598000109195709},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.35740000009536743},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.33090001344680786},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.3278999924659729},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32109999656677246},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3061999976634979},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.30239999294281006},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2996000051498413},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2973000109195709},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.29339998960494995},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.27399998903274536},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2025.3628289","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3628289","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:6b9fa12444dc4796b249b6cee4ea41f4","is_oa":true,"landing_page_url":"https://doaj.org/article/6b9fa12444dc4796b249b6cee4ea41f4","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 13, Pp 189713-189724 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3628289","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3628289","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Cross-modal":[0],"retrieval":[1,16,29,128],"has":[2],"become":[3],"essential":[4],"in":[5,14,27,118,145,174],"establishing":[6],"semantic":[7,94],"correspondences":[8],"between":[9],"heterogeneous":[10],"data":[11,57],"modalities,":[12],"particularly":[13],"text-audio":[15],"applications.":[17],"Generally,":[18],"current":[19],"contrastive":[20,116],"learning-based":[21],"approaches":[22],"(e.g.,":[23],"CLAP)":[24],"perform":[25],"well":[26],"audio":[28],"with":[30],"short":[31],"descriptive":[32],"captions.":[33],"However,":[34],"their":[35],"effectiveness":[36],"significantly":[37],"degrades":[38],"when":[39],"handling":[40],"lengthy":[41],"textual":[42],"descriptions,":[43,148],"subjective":[44],"queries,":[45,151],"and":[46,55,100,152,165,180],"complex":[47,176],"acoustic":[48,154],"environments,":[49],"due":[50],"to":[51,77,121,141],"inherent":[52],"architectural":[53],"limitations":[54],"training":[56,117],"biases.":[58],"To":[59],"address":[60],"these":[61,175],"issues,":[62],"we":[63,133],"propose":[64],"Nanami,":[65,160],"a":[66,92,137],"novel":[67],"framework":[68],"that":[69,159],"capitalizes":[70],"on":[71],"multimodal":[72,80],"large":[73],"language":[74],"models":[75],"(MLLMs)":[76],"produce":[78],"unified":[79],"embedding":[81],"through":[82,114],"two":[83],"synergistic":[84],"mechanisms.":[85],"First,":[86],"Nanami":[87,112],"aligns":[88],"different":[89],"modalities":[90],"into":[91],"shared":[93],"space":[95,120],"via":[96],"designed":[97,140],"prompting":[98],"strategies":[99],"in-context":[101],"learning":[102],"(ICL)":[103],"examples,":[104],"thereby":[105],"effectively":[106],"bridging":[107],"the":[108,163],"modality":[109],"gap.":[110],"Second,":[111],"refines":[113],"unimodal":[115],"this":[119],"enable":[122],"efficient":[123],"hybrid":[124],"encoding,":[125],"achieving":[126],"strong":[127],"performance.":[129],"For":[130],"comprehensive":[131],"evaluation,":[132],"also":[134],"introduce":[135],"Nanamin,":[136],"new":[138],"benchmark":[139],"assess":[142],"model":[143],"capabilities":[144,167],"processing":[146],"long-form":[147],"subjectively":[149],"expressed":[150],"diverse":[153],"samples.":[155],"Experimental":[156],"results":[157],"confirm":[158],"by":[161],"utilizing":[162],"reasoning":[164],"generalization":[166],"of":[168],"MLLMs,":[169],"achieves":[170],"consistently":[171],"robust":[172],"performance":[173],"tasks.":[177],"The":[178],"code":[179],"dataset":[181],"will":[182],"be":[183],"available":[184],"soon.":[185]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-11-03T00:00:00"}