{"id":"https://openalex.org/W7154727656","doi":"https://doi.org/10.1109/iwcia68353.2025.11479780","title":"Integrating Large Language Models and Vector Databases for Podcast Semantic Search","display_name":"Integrating Large Language Models and Vector Databases for Podcast Semantic Search","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7154727656","doi":"https://doi.org/10.1109/iwcia68353.2025.11479780"},"language":null,"primary_location":{"id":"doi:10.1109/iwcia68353.2025.11479780","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwcia68353.2025.11479780","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 14th International Workshop on Computational Intelligence and Applications (IWCIA)","raw_type":"proceedings-article"},"type":"article","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/A5133914320","display_name":"I-Ting Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I185940356","display_name":"Soochow University","ror":"https://ror.org/05kvm7n82","country_code":"TW","type":"education","lineage":["https://openalex.org/I185940356"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"I-Ting Lin","raw_affiliation_strings":["Soochow University,Department of Data Science,Taipei,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Soochow University,Department of Data Science,Taipei,Taiwan","institution_ids":["https://openalex.org/I185940356"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081671158","display_name":"Chia-Hao Chiu","orcid":null},"institutions":[{"id":"https://openalex.org/I185940356","display_name":"Soochow University","ror":"https://ror.org/05kvm7n82","country_code":"TW","type":"education","lineage":["https://openalex.org/I185940356"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chia-Hao Chiu","raw_affiliation_strings":["Soochow University,Department of Data Science,Taipei,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Soochow University,Department of Data Science,Taipei,Taiwan","institution_ids":["https://openalex.org/I185940356"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133917858","display_name":"Bo-Tang Liao","orcid":null},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Bo-Tang Liao","raw_affiliation_strings":["National Cheng Kung University,Department of Computer Science and Information Engineering,Tainan,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Cheng Kung University,Department of Computer Science and Information Engineering,Tainan,Taiwan","institution_ids":["https://openalex.org/I91807558"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5133833321","display_name":"Bo-Jyun Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Bo-Jyun Chen","raw_affiliation_strings":["National Yang Ming Chiao Tung University,Department of Photonics,Hsinchu,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University,Department of Photonics,Hsinchu,Taiwan","institution_ids":["https://openalex.org/I148366613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.83539567,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7","last_page":"14"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.12189999967813492,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12016","display_name":"Web Data Mining and Analysis","score":0.12189999967813492,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.056699998676776886,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T14427","display_name":"Environmental Monitoring and Data Management","score":0.04560000076889992,"subfield":{"id":"https://openalex.org/subfields/1907","display_name":"Geology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.44859999418258667},{"id":"https://openalex.org/keywords/semantic-data-model","display_name":"Semantic data model","score":0.41110000014305115},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3686999976634979},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.36730000376701355},{"id":"https://openalex.org/keywords/language-identification","display_name":"Language identification","score":0.3668999969959259},{"id":"https://openalex.org/keywords/vector-space-model","display_name":"Vector space model","score":0.32199999690055847},{"id":"https://openalex.org/keywords/semantic-search","display_name":"Semantic search","score":0.31520000100135803},{"id":"https://openalex.org/keywords/query-language","display_name":"Query language","score":0.3070000112056732}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7815999984741211},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5860000252723694},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5559999942779541},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4814000129699707},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.44859999418258667},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.41110000014305115},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3686999976634979},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.36730000376701355},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.3668999969959259},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3504999876022339},{"id":"https://openalex.org/C89686163","wikidata":"https://www.wikidata.org/wiki/Q1187982","display_name":"Vector space model","level":2,"score":0.32199999690055847},{"id":"https://openalex.org/C166423231","wikidata":"https://www.wikidata.org/wiki/Q1891170","display_name":"Semantic search","level":3,"score":0.31520000100135803},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.3070000112056732},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.29249998927116394},{"id":"https://openalex.org/C100463513","wikidata":"https://www.wikidata.org/wiki/Q5227322","display_name":"Data model (GIS)","level":2,"score":0.2919999957084656},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2808000147342682},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2759999930858612},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27469998598098755},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C83479923","wikidata":"https://www.wikidata.org/wiki/Q2063748","display_name":"Universal Networking Language","level":4,"score":0.25450000166893005},{"id":"https://openalex.org/C2777946921","wikidata":"https://www.wikidata.org/wiki/Q7449044","display_name":"Semantic analysis (machine learning)","level":2,"score":0.25360000133514404},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iwcia68353.2025.11479780","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwcia68353.2025.11479780","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 14th International Workshop on Computational Intelligence and Applications (IWCIA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5418993830680847,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W310870729","https://openalex.org/W1568335148","https://openalex.org/W1970111434","https://openalex.org/W1984076147","https://openalex.org/W2009579629","https://openalex.org/W2109065059","https://openalex.org/W2113257260","https://openalex.org/W2399614360","https://openalex.org/W2732994307","https://openalex.org/W2970641574","https://openalex.org/W2972584841","https://openalex.org/W3021397474","https://openalex.org/W3113822960","https://openalex.org/W3154081527","https://openalex.org/W4281957013","https://openalex.org/W4394877112","https://openalex.org/W4401834466","https://openalex.org/W4410492435","https://openalex.org/W4412886861"],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,101,104,117,160,182],"rapid":[2],"growth":[3],"of":[4,103,129,148,162],"podcast":[5,45,59,170],"consumption,":[6],"traditional":[7,121],"keyword-based":[8],"search":[9,47,122,171],"methods":[10],"face":[11],"inherent":[12],"limitations":[13],"in":[14],"handling":[15],"unstructured":[16],"audio":[17,191],"data.":[18],"Existing":[19],"systems":[20],"often":[21],"rely":[22],"on":[23,108,133],"metadata":[24],"or":[25],"ASR":[26],"transcripts,":[27],"which":[28],"are":[29],"error-prone":[30],"and":[31,68,80,86,95,113,154,172,179],"fail":[32],"to":[33,168],"capture":[34],"deeper":[35],"semantics.":[36],"To":[37],"address":[38],"these":[39],"challenges,":[40],"this":[41],"study":[42],"proposes":[43],"a":[44,74,125,134,144,186],"semantic":[46,64,90,145,152,176],"system":[48,72,118,184],"that":[49],"integrates":[50],"Large":[51],"Language":[52],"Models":[53],"(LLMs)":[54],"with":[55,165],"vector":[56,84,166],"databases.":[57],"Transcribed":[58],"text":[60],"is":[61],"transformed":[62],"into":[63],"embeddings,":[65],"enabling":[66],"context-aware":[67],"personalized":[69],"retrieval.":[70,173,192],"The":[71],"follows":[73],"two-stage":[75],"workflow:":[76],"(1)":[77],"offline":[78],"transcription":[79],"embedding":[81],"generation":[82],"for":[83,189],"indexing,":[85],"(2)":[87],"online":[88],"real-time":[89],"retrieval":[91],"through":[92],"similarity":[93],"matching":[94],"LLM-based":[96],"refinement.":[97],"Experimental":[98],"results":[99],"validate":[100],"effectiveness":[102],"proposed":[105,183],"approach.":[106],"Based":[107],"238":[109],"valid":[110],"survey":[111],"responses":[112],"100":[114],"controlled":[115],"queries,":[116],"significantly":[119],"outperformed":[120],"methods,":[123],"achieving":[124],"mean":[126],"relevance":[127],"score":[128,146],"5.62":[130],"versus":[131],"1.17":[132],"1-7":[135],"scale":[136],"<tex":[137],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[138],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$(t=8.665,":[139],"p&lt;0.0001)$</tex>.":[140],"It":[141],"also":[142],"reached":[143],"ratio":[147],"82.62%,":[149],"reflecting":[150],"improved":[151],"precision":[153],"user":[155],"satisfaction.":[156],"These":[157],"findings":[158],"demonstrate":[159],"potential":[161],"combining":[163],"LLMs":[164],"databases":[167],"advance":[169],"By":[174],"enhancing":[175],"relevance,":[177],"adaptability,":[178],"user-centered":[180],"reliability,":[181],"provides":[185],"robust":[187],"framework":[188],"intelligent":[190]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-04-18T00:00:00"}