{"id":"https://openalex.org/W4406461722","doi":"https://doi.org/10.1109/slt61566.2024.10832363","title":"Zero-Shot Audio Topic Reranking Using Large Language Models","display_name":"Zero-Shot Audio Topic Reranking Using Large Language Models","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461722","doi":"https://doi.org/10.1109/slt61566.2024.10832363"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832363","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832363","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.repository.cam.ac.uk/bitstreams/665809ee-c94a-456b-b214-675368ecd8eb/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027476226","display_name":"Mengjie Qian","orcid":"https://orcid.org/0000-0003-2614-5411"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Mengjie Qian","raw_affiliation_strings":["Cambridge University,ALTA Institute, Machine Intelligence Lab,Department of Engineering,UK"],"affiliations":[{"raw_affiliation_string":"Cambridge University,ALTA Institute, Machine Intelligence Lab,Department of Engineering,UK","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021875467","display_name":"Rao Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Rao Ma","raw_affiliation_strings":["Cambridge University,ALTA Institute, Machine Intelligence Lab,Department of Engineering,UK"],"affiliations":[{"raw_affiliation_string":"Cambridge University,ALTA Institute, Machine Intelligence Lab,Department of Engineering,UK","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011907463","display_name":"Adian Liusie","orcid":null},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Adian Liusie","raw_affiliation_strings":["Cambridge University,ALTA Institute, Machine Intelligence Lab,Department of Engineering,UK"],"affiliations":[{"raw_affiliation_string":"Cambridge University,ALTA Institute, Machine Intelligence Lab,Department of Engineering,UK","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042184515","display_name":"Erfan Loweimi","orcid":"https://orcid.org/0000-0002-8761-021X"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Erfan Loweimi","raw_affiliation_strings":["Cambridge University,ALTA Institute, Machine Intelligence Lab,Department of Engineering,UK"],"affiliations":[{"raw_affiliation_string":"Cambridge University,ALTA Institute, Machine Intelligence Lab,Department of Engineering,UK","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111076409","display_name":"Kate Knill","orcid":null},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Kate M. Knill","raw_affiliation_strings":["Cambridge University,ALTA Institute, Machine Intelligence Lab,Department of Engineering,UK"],"affiliations":[{"raw_affiliation_string":"Cambridge University,ALTA Institute, Machine Intelligence Lab,Department of Engineering,UK","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050766679","display_name":"Mark Gales","orcid":"https://orcid.org/0000-0002-5311-8219"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mark J.F. Gales","raw_affiliation_strings":["Cambridge University,ALTA Institute, Machine Intelligence Lab,Department of Engineering,UK"],"affiliations":[{"raw_affiliation_string":"Cambridge University,ALTA Institute, Machine Intelligence Lab,Department of Engineering,UK","institution_ids":["https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5027476226"],"corresponding_institution_ids":["https://openalex.org/I241749"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.28089233,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1099","last_page":"1106"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9943000078201294,"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":0.977400004863739,"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":0.6708643436431885},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.6444991827011108},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.584805965423584},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.42081785202026367},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39467543363571167},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3372449278831482},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11408984661102295}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6708643436431885},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6444991827011108},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.584805965423584},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42081785202026367},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39467543363571167},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3372449278831482},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11408984661102295},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/slt61566.2024.10832363","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832363","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},{"id":"pmh:oai:www.repository.cam.ac.uk:1810/374709","is_oa":true,"landing_page_url":"https://www.repository.cam.ac.uk/handle/1810/374709","pdf_url":"https://www.repository.cam.ac.uk/bitstreams/665809ee-c94a-456b-b214-675368ecd8eb/download","source":{"id":"https://openalex.org/S4306401777","display_name":"Apollo (University of Cambridge)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I241749","host_organization_name":"University of Cambridge","host_organization_lineage":["https://openalex.org/I241749"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Object"},{"id":"doi:10.17863/cam.112671","is_oa":true,"landing_page_url":"https://doi.org/10.17863/cam.112671","pdf_url":null,"source":{"id":"https://openalex.org/S7407050737","display_name":"Apollo","issn_l":null,"issn":[],"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","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:www.repository.cam.ac.uk:1810/374709","is_oa":true,"landing_page_url":"https://www.repository.cam.ac.uk/handle/1810/374709","pdf_url":"https://www.repository.cam.ac.uk/bitstreams/665809ee-c94a-456b-b214-675368ecd8eb/download","source":{"id":"https://openalex.org/S4306401777","display_name":"Apollo (University of Cambridge)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I241749","host_organization_name":"University of Cambridge","host_organization_lineage":["https://openalex.org/I241749"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Object"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4024274173","display_name":"Multimodal Video Search by Examples","funder_award_id":"EP/V006223/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G4598575966","display_name":null,"funder_award_id":"EP/V006223/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320320273","display_name":"University of Cambridge","ror":"https://ror.org/013meh722"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4406461722.pdf","grobid_xml":"https://content.openalex.org/works/W4406461722.grobid-xml"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W1984076147","https://openalex.org/W2069870183","https://openalex.org/W2596180971","https://openalex.org/W2783457476","https://openalex.org/W2965373594","https://openalex.org/W2970641574","https://openalex.org/W3043840704","https://openalex.org/W3100107515","https://openalex.org/W3118831779","https://openalex.org/W3197828817","https://openalex.org/W4226278401","https://openalex.org/W4288089799","https://openalex.org/W4307079201","https://openalex.org/W4322718191","https://openalex.org/W4362515116","https://openalex.org/W4368755400","https://openalex.org/W4380302379","https://openalex.org/W4380353763","https://openalex.org/W4384644024","https://openalex.org/W4384918448","https://openalex.org/W4389519598","https://openalex.org/W4389523765","https://openalex.org/W4392637199","https://openalex.org/W4399418426","https://openalex.org/W4401043313","https://openalex.org/W4402112243","https://openalex.org/W4402684223","https://openalex.org/W4404783381","https://openalex.org/W6682631176","https://openalex.org/W6761205521","https://openalex.org/W6766673545","https://openalex.org/W6769627184","https://openalex.org/W6788088100","https://openalex.org/W6810738896","https://openalex.org/W6847076894","https://openalex.org/W6847363464","https://openalex.org/W6850625674","https://openalex.org/W6851775633","https://openalex.org/W6852053240","https://openalex.org/W6852874933","https://openalex.org/W6853799172","https://openalex.org/W6854866820","https://openalex.org/W6855218505","https://openalex.org/W6925375166"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W4298312966","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Multimodal":[0],"Video":[1],"Search":[2],"by":[3,59,79],"Examples":[4],"(MVSE)":[5],"investigates":[6],"using":[7,88],"video":[8,61,101,115],"clips":[9],"as":[10,31,95,147],"the":[11,19,117,163,179],"query":[12],"term":[13],"for":[14,41,70,108,149],"information":[15,140,180],"retrieval,":[16],"rather":[17],"than":[18],"more":[20],"traditional":[21],"text":[22,170],"query.":[23],"This":[24,65],"enables":[25],"far":[26],"richer":[27],"search":[28,49,78],"modalities":[29],"such":[30],"images,":[32],"speaker,":[33],"content,":[34],"topic,":[35],"and":[36,47,145,159,166],"emotion.":[37],"A":[38],"key":[39],"element":[40],"this":[42,75],"process":[43],"is":[44,57,106],"highly":[45],"rapid":[46,76],"flexible":[48],"to":[50,68,99,177],"support":[51],"large":[52,89],"archives,":[53],"which":[54],"in":[55],"MVSE":[56],"facilitated":[58],"representing":[60],"attributes":[62],"with":[63],"embeddings.":[64],"work":[66],"aims":[67],"compensate":[69],"any":[71,100,131],"performance":[72,164],"loss":[73],"from":[74],"archive":[77,102],"examining":[80],"reranking":[81,86,124,151],"approaches.":[82],"In":[83],"particular,":[84],"zero-shot":[85],"methods":[87],"language":[90],"models":[91],"(LLMs)":[92],"are":[93,97],"investigated":[94],"these":[96,169],"applicable":[98],"audio":[103],"content.":[104],"Performance":[105],"evaluated":[107],"topic-based":[109],"retrieval":[110,127],"on":[111],"a":[112,156,174],"publicly":[113],"available":[114],"archive,":[116],"BBC":[118],"Rewind":[119],"corpus.":[120],"Results":[121],"demonstrate":[122],"that":[123],"significantly":[125],"improves":[126],"ranking":[128],"without":[129],"requiring":[130],"task-specific":[132],"in-domain":[133],"training":[134],"data.":[135],"Furthermore,":[136],"three":[137],"sources":[138],"of":[139,168],"(ASR":[141],"transcriptions,":[142],"automatic":[143],"summaries":[144],"synopses)":[146],"input":[148],"LLM":[150],"were":[152],"compared.":[153],"To":[154],"gain":[155],"deeper":[157],"understanding":[158],"further":[160],"insights":[161],"into":[162],"differences":[165],"limitations":[167],"sources,":[171],"we":[172],"employ":[173],"fact-checking":[175],"approach":[176],"analyse":[178],"consistency":[181],"among":[182],"them.":[183]},"counts_by_year":[],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}