{"id":"https://openalex.org/W4402980768","doi":"https://doi.org/10.1109/icme57554.2024.10688053","title":"MFHCA: Enhancing Speech Emotion Recognition Via Multi-Spatial Fusion and Hierarchical Cooperative Attention","display_name":"MFHCA: Enhancing Speech Emotion Recognition Via Multi-Spatial Fusion and Hierarchical Cooperative Attention","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402980768","doi":"https://doi.org/10.1109/icme57554.2024.10688053"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10688053","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10688053","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","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/A5104285919","display_name":"Xinxin Jiao","orcid":null},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xinxin Jiao","raw_affiliation_strings":["Xinjiang University,School of Computer Science and Technology,Urumqi,China"],"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Computer Science and Technology,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101956412","display_name":"Liejun Wang","orcid":"https://orcid.org/0000-0002-3210-0917"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liejun Wang","raw_affiliation_strings":["Xinjiang University,School of Computer Science and Technology,Urumqi,China"],"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Computer Science and Technology,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091800151","display_name":"Yingfeng Yu","orcid":"https://orcid.org/0000-0002-2607-0416"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinfeng Yu","raw_affiliation_strings":["Xinjiang University,School of Computer Science and Technology,Urumqi,China"],"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Computer Science and Technology,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5104285919"],"corresponding_institution_ids":["https://openalex.org/I96908189"],"apc_list":null,"apc_paid":null,"fwci":7.0437,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.97417762,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"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":0.9641000032424927,"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":0.9641000032424927,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9513999819755554,"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":0.706855058670044},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.625478982925415},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5686492919921875},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.4943106174468994},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37286484241485596},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3336777091026306},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06466293334960938}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.706855058670044},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.625478982925415},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5686492919921875},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4943106174468994},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37286484241485596},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3336777091026306},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06466293334960938},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme57554.2024.10688053","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10688053","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320337495","display_name":"Technology Development","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2032254851","https://openalex.org/W2146334809","https://openalex.org/W2586291442","https://openalex.org/W2973049979","https://openalex.org/W3011859875","https://openalex.org/W3015489952","https://openalex.org/W3015884429","https://openalex.org/W3096723250","https://openalex.org/W3160039712","https://openalex.org/W3162475537","https://openalex.org/W3197156295","https://openalex.org/W3209059054","https://openalex.org/W3215440557","https://openalex.org/W4205755002","https://openalex.org/W4221162793","https://openalex.org/W4221162872","https://openalex.org/W4224917001","https://openalex.org/W4372266023","https://openalex.org/W4372266717","https://openalex.org/W4372267501","https://openalex.org/W4375869114"],"related_works":["https://openalex.org/W2099421762","https://openalex.org/W2530546662","https://openalex.org/W2967030268","https://openalex.org/W2185253430","https://openalex.org/W4210345652","https://openalex.org/W1984333081","https://openalex.org/W2945063165","https://openalex.org/W3188962172","https://openalex.org/W3126677997","https://openalex.org/W1610857240"],"abstract_inverted_index":{"Speech":[0,26],"emotion":[1],"recognition":[2],"is":[3],"crucial":[4],"in":[5],"human-computer":[6],"interaction,":[7],"but":[8],"extracting":[9],"and":[10,32,38,54,87,90,97],"using":[11,29],"emotional":[12],"cues":[13],"from":[14,75],"audio":[15],"poses":[16],"challenges.":[17],"This":[18],"paper":[19],"introduces":[20],"MFHCA,":[21],"a":[22,66],"novel":[23],"method":[24,82],"for":[25,58],"Emotion":[27],"Recognition":[28],"Multi-Spatial":[30,44],"Fusion":[31,45],"Hierarchical":[33,67],"Cooperative":[34,68],"Attention":[35,69],"on":[36,83,93],"spectrograms":[37],"raw":[39],"audio.":[40],"We":[41,79],"employ":[42],"the":[43,84,94,104,107],"module":[46,70],"(MF)":[47],"to":[48,72],"efficiently":[49],"identify":[50],"emotion-related":[51],"spectrogram":[52],"regions":[53],"integrate":[55],"Hubert":[56],"features":[57,74],"higher-level":[59],"acoustic":[60],"information.":[61],"Our":[62],"approach":[63],"also":[64],"includes":[65],"(HCA)":[71],"merge":[73],"various":[76],"auditory":[77],"levels.":[78],"evaluate":[80],"our":[81],"IEMOCAP":[85],"dataset":[86],"achieve":[88],"2.6%":[89],"1.87%":[91],"improvements":[92],"weighted":[95],"accuracy":[96],"unweighted":[98],"accuracy,":[99],"respectively.":[100],"Extensive":[101],"experiments":[102],"demonstrate":[103],"effectiveness":[105],"of":[106],"proposed":[108],"method.":[109]},"counts_by_year":[{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":4}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}