{"id":"https://openalex.org/W4297841384","doi":"https://doi.org/10.21437/interspeech.2022-11323","title":"Deep CNN-based Inductive Transfer Learning for Sarcasm Detection in Speech","display_name":"Deep CNN-based Inductive Transfer Learning for Sarcasm Detection in Speech","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4297841384","doi":"https://doi.org/10.21437/interspeech.2022-11323"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-11323","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-11323","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://pure.rug.nl/ws/files/701072351/gao22f_interspeech.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101560145","display_name":"Xiyuan Gao","orcid":"https://orcid.org/0000-0003-0870-6721"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Xiyuan Gao","raw_affiliation_strings":[],"raw_orcid":null,"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":[],"raw_orcid":null,"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":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101560145"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3634,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.50865596,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2323","last_page":"2327"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9916999936103821,"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/T10860","display_name":"Speech and Audio Processing","score":0.9916999936103821,"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":0.95660001039505,"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/T11665","display_name":"Animal Vocal Communication and Behavior","score":0.9345999956130981,"subfield":{"id":"https://openalex.org/subfields/1309","display_name":"Developmental Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/sarcasm","display_name":"Sarcasm","score":0.9090890884399414},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.6670606136322021},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6610135436058044},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6093940734863281},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.533944308757782},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.45999467372894287},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06976774334907532}],"concepts":[{"id":"https://openalex.org/C2776207355","wikidata":"https://www.wikidata.org/wiki/Q191035","display_name":"Sarcasm","level":3,"score":0.9090890884399414},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.6670606136322021},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6610135436058044},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6093940734863281},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.533944308757782},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.45999467372894287},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06976774334907532},{"id":"https://openalex.org/C2779975665","wikidata":"https://www.wikidata.org/wiki/Q131361","display_name":"Irony","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2022-11323","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-11323","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.rug.nl:publications/8fd51bf4-bc67-49fd-b3ba-3c444b37d675","is_oa":true,"landing_page_url":"https://research.rug.nl/en/publications/8fd51bf4-bc67-49fd-b3ba-3c444b37d675","pdf_url":"https://pure.rug.nl/ws/files/701072351/gao22f_interspeech.pdf","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":"Gao, X, Nayak, S & Coler, M 2022, Deep CNN-based Inductive Transfer Learning for Sarcasm Detection in Speech. in Proceedings of Interspeech 2022. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, ISCA, pp. 2323-2327, 23rd Interspeech Conference, Incheon, Korea, Democratic People's Republic of, 18/09/2022. https://doi.org/10.21437/Interspeech.2022-11323","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:pure.rug.nl:openaire/8fd51bf4-bc67-49fd-b3ba-3c444b37d675","is_oa":true,"landing_page_url":"https://hdl.handle.net/11370/8fd51bf4-bc67-49fd-b3ba-3c444b37d675","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":"Gao, X, Nayak, S & Coler, M 2022, Deep CNN-based Inductive Transfer Learning for Sarcasm Detection in Speech. in Proceedings of Interspeech 2022. ISCA, pp. 2323-2327, 23rd Interspeech Conference, Incheon, Korea, Democratic People's Republic of, 18/09/2022. < https://www.isca-speech.org/archive/pdfs/interspeech_2022/gao22f_interspeech.pdf >","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:pure.rug.nl:publications/8fd51bf4-bc67-49fd-b3ba-3c444b37d675","is_oa":true,"landing_page_url":"https://research.rug.nl/en/publications/8fd51bf4-bc67-49fd-b3ba-3c444b37d675","pdf_url":"https://pure.rug.nl/ws/files/701072351/gao22f_interspeech.pdf","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":"Gao, X, Nayak, S & Coler, M 2022, Deep CNN-based Inductive Transfer Learning for Sarcasm Detection in Speech. in Proceedings of Interspeech 2022. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, ISCA, pp. 2323-2327, 23rd Interspeech Conference, Incheon, Korea, Democratic People's Republic of, 18/09/2022. https://doi.org/10.21437/Interspeech.2022-11323","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[{"score":0.6600000262260437,"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4297841384.pdf","grobid_xml":"https://content.openalex.org/works/W4297841384.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3192840557","https://openalex.org/W2889705046","https://openalex.org/W2949280030","https://openalex.org/W2953350812","https://openalex.org/W2997709384","https://openalex.org/W3166467183","https://openalex.org/W4213299466","https://openalex.org/W3091976719","https://openalex.org/W3189091156","https://openalex.org/W4288084884"],"abstract_inverted_index":{"Sarcasm":[0],"is":[1,8,47,94,127],"a":[2,11,48,66,97,130,152],"frequently":[3],"used":[4,35,95,109],"linguistic":[5],"device":[6],"which":[7,114,126,140],"expressed":[9],"in":[10,36,43,58,85,100,133,168,172],"multitude":[12],"of":[13,39,51,68],"ways,":[14],"both":[15],"with":[16],"acoustic":[17],"cues":[18,26,34],"(including":[19,27],"pitch,":[20],"intonation,":[21],"intensity,":[22],"etc.)":[23],"and":[24,112,119,145,166],"visual":[25,118],"facial":[28],"expression,":[29],"eye":[30],"gaze,":[31],"etc.).":[32],"While":[33],"the":[37,44,90,134,157],"expression":[38],"sarcasm":[40,56,84,170],"are":[41,110],"well-described":[42],"literature,":[45],"there":[46],"striking":[49],"paucity":[50],"attempts":[52],"to":[53,82,156],"perform":[54],"automatic":[55],"detection":[57,171],"speech.":[59,86,173],"To":[60,87],"explore":[61],"this":[62,101],"gap,":[63],"we":[64,115],"elaborate":[65],"methodology":[67],"implementing":[69],"Inductive":[70],"Transfer":[71],"Learning":[72],"(ITL)":[73],"based":[74],"on":[75,117],"pre-trained":[76,106],"Deep":[77],"Convolutional":[78],"Neural":[79],"Networks":[80],"(DCNNs)":[81],"detect":[83],"those":[88],"ends,":[89],"multimodal":[91],"dataset":[92,99],"MUStARD":[93],"as":[96,129],"target":[98],"study.":[102],"The":[103],"two":[104],"selected":[105],"DCNN":[107],"models":[108,150],"Xception":[111],"VGGish,":[113,125],"trained":[116],"audio":[120],"datasets.":[121],"Results":[122],"show":[123],"that":[124],"applied":[128],"feature":[131],"extractor":[132],"experiment,":[135],"performs":[136],"better":[137],"than":[138],"Xception,":[139],"has":[141],"its":[142],"convolutional":[143],"layers":[144,147],"pooling":[146],"retrained.":[148],"Both":[149],"achieve":[151],"higher":[153],"F-score":[154],"compared":[155],"baseline":[158],"Support":[159],"Vector":[160],"Machines":[161],"(SVM)":[162],"model":[163],"by":[164],"7%":[165],"5%":[167],"unimodal":[169]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-05-20T08:49:12.498775","created_date":"2025-10-10T00:00:00"}