{"id":"https://openalex.org/W4372260431","doi":"https://doi.org/10.1109/icassp49357.2023.10097110","title":"Multilevel Transformer for Multimodal Emotion Recognition","display_name":"Multilevel Transformer for Multimodal Emotion Recognition","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260431","doi":"https://doi.org/10.1109/icassp49357.2023.10097110"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10097110","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10097110","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100601602","display_name":"Junyi He","orcid":"https://orcid.org/0000-0002-0047-7963"},"institutions":[{"id":"https://openalex.org/I4210154292","display_name":"Digitech Services (New Zealand)","ror":"https://ror.org/04fjy3t60","country_code":"NZ","type":"company","lineage":["https://openalex.org/I4210154292"]}],"countries":["NZ"],"is_corresponding":true,"raw_author_name":"Junyi He","raw_affiliation_strings":["360 DigiTech,China","360 DigiTech, China"],"affiliations":[{"raw_affiliation_string":"360 DigiTech,China","institution_ids":["https://openalex.org/I4210154292"]},{"raw_affiliation_string":"360 DigiTech, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101296653","display_name":"Meimei Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210154292","display_name":"Digitech Services (New Zealand)","ror":"https://ror.org/04fjy3t60","country_code":"NZ","type":"company","lineage":["https://openalex.org/I4210154292"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Meimei Wu","raw_affiliation_strings":["360 DigiTech,China","360 DigiTech, China"],"affiliations":[{"raw_affiliation_string":"360 DigiTech,China","institution_ids":["https://openalex.org/I4210154292"]},{"raw_affiliation_string":"360 DigiTech, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008131938","display_name":"Meng Li","orcid":"https://orcid.org/0000-0002-7095-0170"},"institutions":[{"id":"https://openalex.org/I4210154292","display_name":"Digitech Services (New Zealand)","ror":"https://ror.org/04fjy3t60","country_code":"NZ","type":"company","lineage":["https://openalex.org/I4210154292"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Meng Li","raw_affiliation_strings":["360 DigiTech,China","360 DigiTech, China"],"affiliations":[{"raw_affiliation_string":"360 DigiTech,China","institution_ids":["https://openalex.org/I4210154292"]},{"raw_affiliation_string":"360 DigiTech, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013617244","display_name":"Xiaobo Zhu","orcid":"https://orcid.org/0000-0001-8487-2620"},"institutions":[{"id":"https://openalex.org/I4210154292","display_name":"Digitech Services (New Zealand)","ror":"https://ror.org/04fjy3t60","country_code":"NZ","type":"company","lineage":["https://openalex.org/I4210154292"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Xiaobo Zhu","raw_affiliation_strings":["360 DigiTech,China","360 DigiTech, China"],"affiliations":[{"raw_affiliation_string":"360 DigiTech,China","institution_ids":["https://openalex.org/I4210154292"]},{"raw_affiliation_string":"360 DigiTech, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100398500","display_name":"Feng Ye","orcid":"https://orcid.org/0000-0003-0005-2073"},"institutions":[{"id":"https://openalex.org/I4210154292","display_name":"Digitech Services (New Zealand)","ror":"https://ror.org/04fjy3t60","country_code":"NZ","type":"company","lineage":["https://openalex.org/I4210154292"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Feng Ye","raw_affiliation_strings":["360 DigiTech,China","360 DigiTech, China"],"affiliations":[{"raw_affiliation_string":"360 DigiTech,China","institution_ids":["https://openalex.org/I4210154292"]},{"raw_affiliation_string":"360 DigiTech, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100601602"],"corresponding_institution_ids":["https://openalex.org/I4210154292"],"apc_list":null,"apc_paid":null,"fwci":1.8283,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.84808716,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9998000264167786,"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":0.9998000264167786,"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"}},{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9993000030517578,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9620000123977661,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7675714492797852},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7520545721054077},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6673524379730225},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.6172393560409546},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5325803756713867},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4856911599636078},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4714554250240326},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36108067631721497},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3605451285839081},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3500678539276123},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09461146593093872}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7675714492797852},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7520545721054077},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6673524379730225},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.6172393560409546},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5325803756713867},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4856911599636078},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4714554250240326},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36108067631721497},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3605451285839081},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3500678539276123},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09461146593093872},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10097110","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10097110","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7300000190734863,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1832693441","https://openalex.org/W2061900096","https://openalex.org/W2062391442","https://openalex.org/W2111926505","https://openalex.org/W2146334809","https://openalex.org/W2156387975","https://openalex.org/W2250539671","https://openalex.org/W2707551695","https://openalex.org/W2747664154","https://openalex.org/W2889462515","https://openalex.org/W2903739847","https://openalex.org/W2962770129","https://openalex.org/W2964243274","https://openalex.org/W2965373594","https://openalex.org/W2972463723","https://openalex.org/W2973049979","https://openalex.org/W3096690837","https://openalex.org/W3128513378","https://openalex.org/W3168391820","https://openalex.org/W3197642003","https://openalex.org/W3197977579","https://openalex.org/W3198528147","https://openalex.org/W4297841880","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6665983271","https://openalex.org/W6682889407","https://openalex.org/W6729654139","https://openalex.org/W6755207826","https://openalex.org/W6766673545","https://openalex.org/W6768021236","https://openalex.org/W6769196770","https://openalex.org/W6780218876","https://openalex.org/W6780493881"],"related_works":["https://openalex.org/W2931688134","https://openalex.org/W2377919138","https://openalex.org/W2529301793","https://openalex.org/W2378857091","https://openalex.org/W2384121599","https://openalex.org/W103652678","https://openalex.org/W4226090359","https://openalex.org/W2038083449","https://openalex.org/W3016124757","https://openalex.org/W3034520363"],"abstract_inverted_index":{"Multimodal":[0],"emotion":[1,30,81],"recognition":[2],"has":[3],"attracted":[4],"much":[5],"attention":[6],"recently.":[7],"Fusing":[8],"multiple":[9],"modalities":[10],"effectively":[11],"with":[12,63,92,105],"limited":[13],"labeled":[14],"data":[15],"is":[16,35],"a":[17,55,73],"challenging":[18],"task.":[19],"Considering":[20],"the":[21],"success":[22],"of":[23,29],"pre-trained":[24,64],"model":[25,76,104,114,123],"and":[26],"fine-grained":[27,61,79],"nature":[28],"expression,":[31],"we":[32,53,71,84,99],"think":[33],"it":[34],"reasonable":[36],"to":[37,77,88],"take":[38],"these":[39],"two":[40],"aspects":[41],"into":[42],"consideration.":[43],"Unlike":[44],"previous":[45,116],"methods":[46,87],"that":[47,111],"mainly":[48],"focus":[49],"on":[50,119],"one":[51],"aspect,":[52],"introduce":[54],"novel":[56],"multi-granularity":[57,97],"framework,":[58],"which":[59],"combines":[60],"representation":[62],"utterance-level":[65],"representation.":[66],"Inspired":[67],"by":[68],"Transformer":[69],"TTS,":[70],"propose":[72],"multilevel":[74,102,112],"transformer":[75,103,113],"perform":[78,96],"multimodal":[80],"recognition.":[82],"Specifically,":[83],"explore":[85],"different":[86],"incorporate":[89],"phoneme-level":[90],"embedding":[91],"word-level":[93],"embedding.":[94],"To":[95],"learning,":[98],"simply":[100],"combine":[101],"Bert.":[106],"Extensive":[107],"experimental":[108],"results":[109],"show":[110],"outperforms":[115],"state-of-the-art":[117],"approaches":[118],"IEMOCAP":[120],"dataset.":[121],"Multi-granularity":[122],"achieves":[124],"additional":[125],"performance":[126],"improvement.":[127]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}