{"id":"https://openalex.org/W3095379519","doi":"https://doi.org/10.21437/interspeech.2020-1653","title":"Multi-Modal Attention for Speech Emotion Recognition","display_name":"Multi-Modal Attention for Speech Emotion Recognition","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3095379519","doi":"https://doi.org/10.21437/interspeech.2020-1653","mag":"3095379519"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1653","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1653","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","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/A5060530570","display_name":"Zexu Pan","orcid":"https://orcid.org/0000-0002-8106-1176"},"institutions":[{"id":"https://openalex.org/I144291393","display_name":"Data Storage Institute","ror":"https://ror.org/03k5xes38","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I144291393"]},{"id":"https://openalex.org/I4210126319","display_name":"Duke-NUS Medical School","ror":"https://ror.org/02j1m6098","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596","https://openalex.org/I170897317","https://openalex.org/I4210126319"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zexu Pan","raw_affiliation_strings":["Institute of Data Science, NUS, Singapore","Graduate School for Integrative Sciences and Engineering, NUS, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Data Science, NUS, Singapore","institution_ids":["https://openalex.org/I144291393"]},{"raw_affiliation_string":"Graduate School for Integrative Sciences and Engineering, NUS, Singapore","institution_ids":["https://openalex.org/I4210126319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077713342","display_name":"Zhaojie Luo","orcid":"https://orcid.org/0000-0002-4173-6319"},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Zhaojie Luo","raw_affiliation_strings":["Osaka University, Osaka, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Osaka University, Osaka, Japan","institution_ids":["https://openalex.org/I98285908"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101406845","display_name":"Jichen Yang","orcid":"https://orcid.org/0000-0003-2655-8304"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jichen Yang","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National University of Singapore (NUS), Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore (NUS), Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I144291393","display_name":"Data Storage Institute","ror":"https://ror.org/03k5xes38","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I144291393"]},{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["Institute of Data Science, NUS, Singapore","Department of Electrical and Computer Engineering, National University of Singapore (NUS), Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Data Science, NUS, Singapore","institution_ids":["https://openalex.org/I144291393"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore (NUS), Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":88,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"364","last_page":"368"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9860000014305115,"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":0.9860000014305115,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.9850999712944031,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9505000114440918,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/speech-recognition","display_name":"Speech recognition","score":0.741095781326294},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6933259963989258},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.6317648887634277},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6060581803321838},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39852532744407654}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.741095781326294},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6933259963989258},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.6317648887634277},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6060581803321838},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39852532744407654},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-1653","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1653","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1133916940","https://openalex.org/W1614298861","https://openalex.org/W1983364832","https://openalex.org/W2016053056","https://openalex.org/W2079725295","https://openalex.org/W2098689807","https://openalex.org/W2110957653","https://openalex.org/W2144005487","https://openalex.org/W2146334809","https://openalex.org/W2154091569","https://openalex.org/W2226884328","https://openalex.org/W2251394420","https://openalex.org/W2533262878","https://openalex.org/W2584561145","https://openalex.org/W2740550900","https://openalex.org/W2752062163","https://openalex.org/W2808359495","https://openalex.org/W2889169802","https://openalex.org/W2918087949","https://openalex.org/W2963104701","https://openalex.org/W2964051877","https://openalex.org/W2964216663","https://openalex.org/W2964326992","https://openalex.org/W2964346351","https://openalex.org/W2972493869","https://openalex.org/W2973110385","https://openalex.org/W2990629080","https://openalex.org/W3099388488","https://openalex.org/W4299280181","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2789919619","https://openalex.org/W2293457016","https://openalex.org/W3169305685","https://openalex.org/W2351428524","https://openalex.org/W2368779261","https://openalex.org/W1551406738","https://openalex.org/W2610387714","https://openalex.org/W2369308426","https://openalex.org/W1569841287","https://openalex.org/W1512718085"],"abstract_inverted_index":{"Emotion":[0],"represents":[1],"an":[2],"essential":[3],"aspect":[4],"of":[5,41,106],"human":[6,21],"speech":[7,12,47,82],"that":[8,81],"is":[9,69,97],"manifested":[10],"in":[11,20,46,75,104],"prosody.Speech,":[13],"visual,":[14],"and":[15,43,64,89,92],"textual":[16,44,90],"cues":[17,45],"are":[18],"complementary":[19],"communication.In":[22],"this":[23],"paper,":[24],"we":[25],"study":[26],"a":[27,51,110],"hybrid":[28,117],"fusion":[29,102],"method,":[30],"referred":[31],"to":[32,38],"as":[33,98,100],"multi-modal":[34],"attention":[35,54,60],"network":[36,114,118],"(MMAN)":[37],"make":[39],"use":[40],"visual":[42,88],"emotion":[48,83,127],"recognition.We":[49],"propose":[50],"novel":[52],"multimodal":[53],"mechanism,":[55],"cLSTM-MMA,":[56],"which":[57],"facilitates":[58],"the":[59,67,76,93],"across":[61],"three":[62],"modalities":[63],"selectively":[65],"fuse":[66],"information.cLSTM-MMA":[68],"fused":[70],"with":[71,109],"other":[72,101],"uni-modal":[73],"subnetworks":[74],"late":[77],"fusion.The":[78],"experiments":[79],"show":[80],"recognition":[84],"benefits":[85],"significantly":[86],"from":[87],"cues,":[91],"proposed":[94,116],"cLSTM-MMA":[95],"alone":[96],"competitive":[99],"methods":[103],"terms":[105],"accuracy,":[107],"but":[108],"much":[111],"more":[112],"compact":[113],"structure.The":[115],"MMAN":[119],"achieves":[120],"state-of-the-art":[121],"performance":[122],"on":[123],"IEMOCAP":[124],"database":[125],"for":[126],"recognition.":[128]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":19},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":19},{"year":2022,"cited_by_count":18},{"year":2021,"cited_by_count":13}],"updated_date":"2026-07-27T08:26:11.824852","created_date":"2025-10-10T00:00:00"}