{"id":"https://openalex.org/W4387968017","doi":"https://doi.org/10.1145/3581783.3612846","title":"Cascaded Cross-Modal Transformer for Request and Complaint Detection","display_name":"Cascaded Cross-Modal Transformer for Request and Complaint Detection","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387968017","doi":"https://doi.org/10.1145/3581783.3612846"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612846","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612846","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","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/A5083932459","display_name":"Nicolae-C\u0103t\u0103lin Ristea","orcid":"https://orcid.org/0000-0002-7880-9307"},"institutions":[{"id":"https://openalex.org/I61641377","display_name":"Universitatea Na\u021bional\u0103 de \u0218tiin\u021b\u0103 \u0219i Tehnologie Politehnica Bucure\u0219ti","ror":"https://ror.org/0558j5q12","country_code":"RO","type":"education","lineage":["https://openalex.org/I61641377"]}],"countries":["RO"],"is_corresponding":true,"raw_author_name":"Nicolae-Catalin Ristea","raw_affiliation_strings":["University Politehnica of Bucharest, Bucharest, Romania"],"affiliations":[{"raw_affiliation_string":"University Politehnica of Bucharest, Bucharest, Romania","institution_ids":["https://openalex.org/I61641377"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081017623","display_name":"Radu Tudor Ionescu","orcid":"https://orcid.org/0000-0002-9301-1950"},"institutions":[{"id":"https://openalex.org/I141595442","display_name":"University of Bucharest","ror":"https://ror.org/02x2v6p15","country_code":"RO","type":"education","lineage":["https://openalex.org/I141595442"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Radu Tudor Ionescu","raw_affiliation_strings":["University of Bucharest, Bucharest, Romania"],"affiliations":[{"raw_affiliation_string":"University of Bucharest, Bucharest, Romania","institution_ids":["https://openalex.org/I141595442"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5083932459"],"corresponding_institution_ids":["https://openalex.org/I61641377"],"apc_list":null,"apc_paid":null,"fwci":0.5237,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.7208279,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"9467","last_page":"9471"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9869999885559082,"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"}},"topics":[{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9869999885559082,"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/T12031","display_name":"Speech and dialogue systems","score":0.9749000072479248,"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/T11121","display_name":"Public Relations and Crisis Communication","score":0.9606999754905701,"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/computer-science","display_name":"Computer science","score":0.7828015089035034},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.7322073578834534},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.719171404838562},{"id":"https://openalex.org/keywords/complaint","display_name":"Complaint","score":0.6720673441886902},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6395821571350098},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5923582911491394},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.41172540187835693},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4061514735221863},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3916870057582855},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.23949921131134033},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10056418180465698},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.0787011981010437},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06675764918327332}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7828015089035034},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.7322073578834534},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.719171404838562},{"id":"https://openalex.org/C2780838233","wikidata":"https://www.wikidata.org/wiki/Q836925","display_name":"Complaint","level":2,"score":0.6720673441886902},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6395821571350098},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5923582911491394},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.41172540187835693},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4061514735221863},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3916870057582855},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.23949921131134033},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10056418180465698},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0787011981010437},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06675764918327332},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3612846","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612846","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2064675550","https://openalex.org/W2194775991","https://openalex.org/W2767290858","https://openalex.org/W2962770129","https://openalex.org/W2986154550","https://openalex.org/W3011727199","https://openalex.org/W3036601975","https://openalex.org/W3103187652","https://openalex.org/W3154596443","https://openalex.org/W3196974791","https://openalex.org/W4206042814","https://openalex.org/W4296068596","https://openalex.org/W4307640249","https://openalex.org/W4387968410"],"related_works":["https://openalex.org/W1885497808","https://openalex.org/W4389612504","https://openalex.org/W2022249118","https://openalex.org/W51147162","https://openalex.org/W3009921285","https://openalex.org/W2046737675","https://openalex.org/W1596393722","https://openalex.org/W2072761933","https://openalex.org/W4327644547","https://openalex.org/W2347345225"],"abstract_inverted_index":{"We":[0,63],"propose":[1],"a":[2,26,57],"novel":[3,58],"cascaded":[4,59],"cross-modal":[5],"transformer":[6,61],"(CCMT)":[7],"that":[8],"combines":[9],"speech":[10,32,35],"and":[11,18,39,86,91],"text":[12],"transcripts":[13,42],"to":[14,67],"detect":[15],"customer":[16],"requests":[17],"complaints":[19],"in":[20,56],"phone":[21],"conversations.":[22],"Our":[23],"approach":[24],"leverages":[25],"multimodal":[27],"paradigm":[28],"by":[29],"transcribing":[30],"the":[31,41,68,72,89],"using":[33],"automatic":[34],"recognition":[36],"(ASR)":[37],"models":[38,51],"translating":[40],"into":[43],"different":[44],"languages.":[45],"Subsequently,":[46],"we":[47],"combine":[48],"language-specific":[49],"BERT-based":[50],"with":[52],"Wav2Vec2.0":[53],"audio":[54],"features":[55],"cross-attention":[60],"model.":[62],"apply":[64],"our":[65],"system":[66],"Requests":[69],"Sub-Challenge":[70],"of":[71,84],"ACM":[73],"Multimedia":[74],"2023":[75],"Computational":[76],"Paralinguistics":[77],"Challenge,":[78],"reaching":[79],"unweighted":[80],"average":[81],"recalls":[82],"(UAR)":[83],"65.41%":[85],"85.87%":[87],"for":[88],"complaint":[90],"request":[92],"classes,":[93],"respectively.":[94]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
