{"id":"https://openalex.org/W4415432861","doi":"https://doi.org/10.21437/interspeech.2025-2074","title":"Leveraging Large Language Models for Sarcastic Speech Annotation in Sarcasm Detection","display_name":"Leveraging Large Language Models for Sarcastic Speech Annotation in Sarcasm Detection","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415432861","doi":"https://doi.org/10.21437/interspeech.2025-2074"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2025-2074","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-2074","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://research.rug.nl/en/publications/5f849184-f847-4c67-87da-1d0cf930635d","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100748869","display_name":"Li Zhu","orcid":"https://orcid.org/0000-0001-5249-6536"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhu Li","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102776935","display_name":"Yuqing Zhang","orcid":"https://orcid.org/0009-0009-0486-6470"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuqing Zhang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101560145","display_name":"Xiyuan Gao","orcid":"https://orcid.org/0000-0003-0870-6721"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiyuan Gao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001110193","display_name":"Shekhar Nayak","orcid":"https://orcid.org/0000-0002-4277-4851"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shekhar Nayak","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5090819693","display_name":"Matt Coler","orcid":"https://orcid.org/0000-0002-7631-5063"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Matt Coler","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100748869"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.38093207,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3973","last_page":"3977"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13912","display_name":"Language, Linguistics, Cultural Analysis","score":0.9855999946594238,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13912","display_name":"Language, Linguistics, Cultural Analysis","score":0.9855999946594238,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13959","display_name":"Swearing, Euphemism, Multilingualism","score":0.9168999791145325,"subfield":{"id":"https://openalex.org/subfields/3315","display_name":"Communication"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/sarcasm","display_name":"Sarcasm","score":0.9868000149726868},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6646000146865845},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5333999991416931},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.5012000203132629},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.445499986410141},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4018999934196472},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.3668000102043152},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.3465000092983246}],"concepts":[{"id":"https://openalex.org/C2776207355","wikidata":"https://www.wikidata.org/wiki/Q191035","display_name":"Sarcasm","level":3,"score":0.9868000149726868},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7742000222206116},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6646000146865845},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6636999845504761},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6301000118255615},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5333999991416931},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.5012000203132629},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.445499986410141},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4018999934196472},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39980000257492065},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3928000032901764},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.3668000102043152},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.3465000092983246},{"id":"https://openalex.org/C2780583480","wikidata":"https://www.wikidata.org/wiki/Q1366327","display_name":"Tone (literature)","level":2,"score":0.3370000123977661},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.33379998803138733},{"id":"https://openalex.org/C2780876879","wikidata":"https://www.wikidata.org/wiki/Q3054749","display_name":"Meaning (existential)","level":2,"score":0.2935999929904938},{"id":"https://openalex.org/C194051981","wikidata":"https://www.wikidata.org/wiki/Q1337691","display_name":"Economic shortage","level":3,"score":0.29010000824928284},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.273499995470047},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.26980000734329224},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.26420000195503235}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2025-2074","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-2074","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.rug.nl:openaire/5f849184-f847-4c67-87da-1d0cf930635d","is_oa":true,"landing_page_url":"https://research.rug.nl/en/publications/5f849184-f847-4c67-87da-1d0cf930635d","pdf_url":null,"source":{"id":"https://openalex.org/S4306400420","display_name":"University of Groningen research database (University of Groningen / Centre for Information Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I169381384","host_organization_name":"University of Groningen","host_organization_lineage":["https://openalex.org/I169381384"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Li, Z, Zhang, Y, Gao, X, Nayak, S & Coler, M 2025, Leveraging Large Language Models for Sarcastic Speech Annotation in Sarcasm Detection. in Proceedings of Interspeech 2025. ISCA, pp. 3973-3977, Interspeech 2025, Rotterdam, Netherlands, 17/08/2025. https://doi.org/10.21437/Interspeech.2025-2074","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:pure.rug.nl:publications/5f849184-f847-4c67-87da-1d0cf930635d","is_oa":true,"landing_page_url":"https://hdl.handle.net/11370/5f849184-f847-4c67-87da-1d0cf930635d","pdf_url":null,"source":{"id":"https://openalex.org/S4306400420","display_name":"University of Groningen research database (University of Groningen / Centre for Information Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I169381384","host_organization_name":"University of Groningen","host_organization_lineage":["https://openalex.org/I169381384"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Li, Z, Zhang, Y, Gao, X, Nayak, S & Coler, M 2025, Leveraging Large Language Models for Sarcastic Speech Annotation in Sarcasm Detection. in Proceedings of Interspeech 2025. ISCA, pp. 3973-3977, Interspeech 2025, Rotterdam, Netherlands, 17/08/2025. https://doi.org/10.21437/Interspeech.2025-2074","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:pure.rug.nl:openaire/5f849184-f847-4c67-87da-1d0cf930635d","is_oa":true,"landing_page_url":"https://research.rug.nl/en/publications/5f849184-f847-4c67-87da-1d0cf930635d","pdf_url":null,"source":{"id":"https://openalex.org/S4306400420","display_name":"University of Groningen research database (University of Groningen / Centre for Information Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I169381384","host_organization_name":"University of Groningen","host_organization_lineage":["https://openalex.org/I169381384"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Li, Z, Zhang, Y, Gao, X, Nayak, S & Coler, M 2025, Leveraging Large Language Models for Sarcastic Speech Annotation in Sarcasm Detection. in Proceedings of Interspeech 2025. ISCA, pp. 3973-3977, Interspeech 2025, Rotterdam, Netherlands, 17/08/2025. https://doi.org/10.21437/Interspeech.2025-2074","raw_type":"info:eu-repo/semantics/publishedVersion"},"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":{"Sarcasm":[0],"fundamentally":[1],"alters":[2],"meaning":[3],"through":[4,114],"tone":[5],"and":[6,68,90],"context,":[7],"yet":[8],"detecting":[9],"it":[10],"in":[11,33],"speech":[12,37,111],"remains":[13],"a":[14,56,60,94,100,108,121,130],"challenge":[15],"due":[16],"to":[17,54,79],"data":[18],"scarcity.":[19],"In":[20],"addition,":[21],"existing":[22],"detection":[23,91,118,134],"systems":[24],"often":[25],"rely":[26],"on":[27,93],"multimodal":[28],"data,":[29],"limiting":[30],"their":[31],"applicability":[32],"contexts":[34],"where":[35],"only":[36],"is":[38],"available.":[39],"To":[40],"address":[41],"this,":[42],"we":[43,65,105],"propose":[44],"an":[45],"annotation":[46,88],"pipeline":[47],"that":[48],"leverages":[49],"large":[50],"language":[51],"models":[52],"(LLMs)":[53],"generate":[55],"sarcasm":[57,73,97,133],"dataset.":[58],"Using":[59],"publicly":[61,95],"available":[62,96],"sarcasm-focused":[63],"podcast,":[64],"employ":[66],"GPT-4o":[67],"LLaMA":[69],"3":[70],"for":[71,132],"initial":[72],"annotations,":[74],"followed":[75],"by":[76,86],"human":[77],"verification":[78],"resolve":[80],"disagreements.":[81],"We":[82],"validate":[83],"this":[84,115],"approach":[85],"comparing":[87],"quality":[89],"performance":[92],"dataset":[98,112],"using":[99],"collaborative":[101],"gating":[102],"architecture.":[103],"Finally,":[104],"introduce":[106],"PodSarc,":[107],"large-scale":[109],"sarcastic":[110],"created":[113],"pipeline.":[116],"The":[117],"model":[119],"achieves":[120],"73.63%":[122],"F1":[123],"score,":[124],"demonstrating":[125],"the":[126],"dataset's":[127],"potential":[128],"as":[129],"benchmark":[131],"research.":[135]},"counts_by_year":[],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-10-24T00:00:00"}