{"id":"https://openalex.org/W4319862466","doi":"https://doi.org/10.1109/slt54892.2023.10022557","title":"Multilingual Speech Emotion Recognition with Multi-Gating Mechanism and Neural Architecture Search","display_name":"Multilingual Speech Emotion Recognition with Multi-Gating Mechanism and Neural Architecture Search","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862466","doi":"https://doi.org/10.1109/slt54892.2023.10022557"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10022557","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10022557","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100380097","display_name":"Zihan Wang","orcid":"https://orcid.org/0000-0001-8606-1733"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zihan Wang","raw_affiliation_strings":["Columbia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101903282","display_name":"Meng Qi","orcid":"https://orcid.org/0000-0003-3609-2560"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qi Meng","raw_affiliation_strings":["Columbia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016243779","display_name":"HaiFeng Lan","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"HaiFeng Lan","raw_affiliation_strings":["Columbia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075234973","display_name":"XinRui Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"XinRui Zhang","raw_affiliation_strings":["Columbia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046064719","display_name":"KeHao Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"KeHao Guo","raw_affiliation_strings":["Columbia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101112531","display_name":"Akshat Gupta","orcid":null},"institutions":[{"id":"https://openalex.org/I1305429384","display_name":"JPMorgan Chase & Co (United States)","ror":"https://ror.org/01x3kkr08","country_code":"US","type":"company","lineage":["https://openalex.org/I1305429384"]},{"id":"https://openalex.org/I2802755631","display_name":"Morgan Stanley (United States)","ror":"https://ror.org/00aphdz18","country_code":"US","type":"company","lineage":["https://openalex.org/I2802755631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Akshat Gupta","raw_affiliation_strings":["JP Morgan AI Research,New York,USA","JP Morgan AI Research, New York, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JP Morgan AI Research,New York,USA","institution_ids":["https://openalex.org/I1305429384","https://openalex.org/I2802755631"]},{"raw_affiliation_string":"JP Morgan AI Research, New York, USA","institution_ids":["https://openalex.org/I1305429384"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3521,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.50516224,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"806","last_page":"813"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9997000098228455,"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":0.9997000098228455,"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/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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/T11309","display_name":"Music and Audio Processing","score":0.9990000128746033,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8141523599624634},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6640452146530151},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5529659390449524},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5215318202972412},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5196896195411682},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.49845147132873535},{"id":"https://openalex.org/keywords/german","display_name":"German","score":0.48374295234680176},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4768756031990051},{"id":"https://openalex.org/keywords/disgust","display_name":"Disgust","score":0.4625953733921051},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.46130162477493286},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.4237777590751648},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11137834191322327},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08171233534812927}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8141523599624634},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6640452146530151},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5529659390449524},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5215318202972412},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5196896195411682},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.49845147132873535},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.48374295234680176},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4768756031990051},{"id":"https://openalex.org/C2777375102","wikidata":"https://www.wikidata.org/wiki/Q208351","display_name":"Disgust","level":3,"score":0.4625953733921051},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.46130162477493286},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.4237777590751648},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11137834191322327},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08171233534812927},{"id":"https://openalex.org/C118552586","wikidata":"https://www.wikidata.org/wiki/Q7867","display_name":"Psychiatry","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C2779302386","wikidata":"https://www.wikidata.org/wiki/Q79871","display_name":"Anger","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt54892.2023.10022557","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10022557","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6800000071525574,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W175750906","https://openalex.org/W639708223","https://openalex.org/W1494198834","https://openalex.org/W1536680647","https://openalex.org/W1966026565","https://openalex.org/W2104094955","https://openalex.org/W2146334809","https://openalex.org/W2159017231","https://openalex.org/W2191779130","https://openalex.org/W2499760652","https://openalex.org/W2553303224","https://openalex.org/W2809290718","https://openalex.org/W2889717020","https://openalex.org/W2896457183","https://openalex.org/W2899663614","https://openalex.org/W2903852246","https://openalex.org/W2914120296","https://openalex.org/W2949264490","https://openalex.org/W2951104886","https://openalex.org/W2951442257","https://openalex.org/W2953356739","https://openalex.org/W2962788625","https://openalex.org/W2963087748","https://openalex.org/W2963828549","https://openalex.org/W2969937244","https://openalex.org/W2970737019","https://openalex.org/W3002872170","https://openalex.org/W3011985699","https://openalex.org/W3015877095","https://openalex.org/W3022013598","https://openalex.org/W3097571315","https://openalex.org/W3160713074","https://openalex.org/W3195507353","https://openalex.org/W3197994565","https://openalex.org/W3198528147","https://openalex.org/W3202667537","https://openalex.org/W3208480086","https://openalex.org/W4212774754","https://openalex.org/W4239943352","https://openalex.org/W4285112472","https://openalex.org/W4287776200","https://openalex.org/W4301204483","https://openalex.org/W4385245566","https://openalex.org/W6729956949","https://openalex.org/W6761176036","https://openalex.org/W6774704184","https://openalex.org/W6779326418","https://openalex.org/W6784488644","https://openalex.org/W6800423299","https://openalex.org/W6801124762"],"related_works":["https://openalex.org/W2955987787","https://openalex.org/W619369203","https://openalex.org/W4386027168","https://openalex.org/W2619202811","https://openalex.org/W2080838132","https://openalex.org/W2018507422","https://openalex.org/W2038612614","https://openalex.org/W2991587272","https://openalex.org/W2120463044","https://openalex.org/W2808907289"],"abstract_inverted_index":{"Speech":[0,18],"emotion":[1,7],"recognition":[2,44],"(SER)":[3,21],"classifies":[4],"audio":[5,122],"into":[6],"categories":[8],"such":[9],"as":[10],"Happy,":[11],"Angry,":[12],"Fear,":[13],"Disgust":[14],"and":[15,62,91,138],"Neutral.":[16],"While":[17],"Emotion":[19],"Recognition":[20],"is":[22],"a":[23,33,50,65,79,103,112],"common":[24],"application":[25],"for":[26,35,72,88,94,99,121,136,140],"popular":[27],"languages,":[28,37],"it":[29],"continues":[30],"to":[31,82,116],"be":[32],"problem":[34],"low-resourced":[36],"i.e.,":[38],"languages":[39],"with":[40],"no":[41],"pre-trained":[42,59],"speech-to-text":[43],"models.":[45],"This":[46],"paper":[47],"firstly":[48],"proposes":[49],"language-specific":[51],"model":[52,67,77,129],"that":[53,68,127],"extract":[54],"emotional":[55],"information":[56],"from":[57],"multiple":[58],"speech":[60],"models,":[61],"then":[63],"designs":[64],"multi-domain":[66,76],"simultaneously":[69],"performs":[70],"SER":[71],"various":[73],"languages.":[74],"Our":[75,124],"employs":[78],"multi-gating":[80],"mechanism":[81],"generate":[83],"unique":[84],"weighted":[85],"feature":[86],"combination":[87],"each":[89,100],"language,":[90],"also":[92],"searches":[93],"specific":[95],"neural":[96,104],"network":[97],"structure":[98],"language":[101],"through":[102],"architecture":[105],"search":[106],"module.":[107],"In":[108],"addition,":[109],"we":[110],"introduce":[111],"contrastive":[113],"auxiliary":[114],"loss":[115],"build":[117],"more":[118],"separable":[119],"rep-resentations":[120],"data.":[123],"experiments":[125],"show":[126],"our":[128],"raises":[130],"the":[131],"state-of-the-art":[132],"accuracy":[133],"by":[134],"3%":[135],"German":[137],"14.3%":[139],"French.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}