{"id":"https://openalex.org/W4385822618","doi":"https://doi.org/10.21437/interspeech.2023-463","title":"Fine-tuned RoBERTa Model with a CNN-LSTM Network for Conversational Emotion Recognition","display_name":"Fine-tuned RoBERTa Model with a CNN-LSTM Network for Conversational Emotion Recognition","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385822618","doi":"https://doi.org/10.21437/interspeech.2023-463"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-463","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-463","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","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/A5056746787","display_name":"Jiachen Luo","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jiachen Luo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101798122","display_name":"Huy Phan","orcid":"https://orcid.org/0000-0002-7011-5511"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huy Phan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5111403298","display_name":"Joshua D. Reiss","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Joshua Reiss","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5056746787"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0431,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.77658089,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2413","last_page":"2417"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.7986000180244446,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.7986000180244446,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7726720571517944},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.6399575471878052},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5844045877456665},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45109084248542786},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3928719758987427},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.38564759492874146}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7726720571517944},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.6399575471878052},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5844045877456665},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45109084248542786},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3928719758987427},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.38564759492874146}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2023-463","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-463","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"},{"id":"pmh:oai:qmro.qmul.ac.uk:123456789/97991","is_oa":false,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/97991","pdf_url":null,"source":{"id":"https://openalex.org/S4306400530","display_name":"Queen Mary Research Online (Queen Mary University of London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I166337079","host_organization_name":"Queen Mary University of London","host_organization_lineage":["https://openalex.org/I166337079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceeding"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3188962172","https://openalex.org/W2772917594","https://openalex.org/W4306742369","https://openalex.org/W4303457083","https://openalex.org/W2131146434","https://openalex.org/W2536562190","https://openalex.org/W2951359407","https://openalex.org/W3204019825","https://openalex.org/W3126677997","https://openalex.org/W1610857240"],"abstract_inverted_index":{"Textual":[0],"emotion":[1,90,127,136],"recognition":[2,91],"in":[3,9,56,92,128],"conversations":[4],"has":[5],"gained":[6],"increasing":[7],"attention":[8],"recent":[10],"years":[11],"for":[12,88],"the":[13,43,97,114,140,158],"growing":[14],"amount":[15],"of":[16,51,150],"applications":[17],"it":[18],"can":[19],"serve,":[20],"e.g.,":[21],"human-robot":[22],"interactions,":[23],"recommended":[24],"systems.":[25],"However,":[26],"most":[27],"existing":[28],"approaches":[29],"are":[30,123,132],"either":[31],"based":[32,78],"on":[33,79,134],"BERT-based":[34],"model":[35,83,100,145],"which":[36],"fail":[37],"to":[38,48,101,125],"exploit":[39],"crucial":[40],"information":[41],"about":[42],"long-text":[44],"context,":[45],"or":[46],"resort":[47],"complex":[49],"entanglement":[50],"neural":[52,110],"network":[53,87,111],"architectures":[54],"resulting":[55],"less":[57],"stable":[58],"training":[59],"procedures":[60],"and":[61,75,119,139,153],"slower":[62],"inference":[63],"time.":[64],"To":[65],"bridge":[66],"this":[67],"gap,":[68],"we":[69,95],"first":[70],"propose":[71],"a":[72,85,147],"fast,":[73],"compact":[74],"parameter-efficient":[76],"framework":[77],"fine-tuned":[80],"pre-trained":[81],"RoBERTa":[82,99],"with":[84,113,157],"CNN-LSTM":[86],"textual":[89],"conversations.":[93,129],"First,":[94],"fine-tune":[96],"pre-tranined":[98],"effectively":[102],"learn":[103],"long-term":[104],"emotion-relevant":[105],"context":[106],"information.":[107],"Second,":[108],"convolutional":[109],"coupled":[112],"bidirectional":[115],"long":[116],"short-term":[117],"memory":[118],"joint":[120],"reinforced":[121],"blocks":[122],"utilized":[124],"recognize":[126],"Extensive":[130],"experiments":[131],"conducted":[133],"benchmark":[135],"MELD":[137],"dataset,":[138],"results":[141,156],"show":[142],"that":[143],"our":[144],"outperforms":[146],"wide":[148],"range":[149],"strong":[151],"baselines":[152],"achieves":[154],"competitive":[155],"state-of-art":[159],"approaches.":[160]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}