{"id":"https://openalex.org/W4391992469","doi":"https://doi.org/10.1109/cyberc58899.2023.00034","title":"BS-GSA: Speech Emotion Recognition via Blend-Sample Empowered Global & Spectral Attentive Paradigm","display_name":"BS-GSA: Speech Emotion Recognition via Blend-Sample Empowered Global & Spectral Attentive Paradigm","publication_year":2023,"publication_date":"2023-11-02","ids":{"openalex":"https://openalex.org/W4391992469","doi":"https://doi.org/10.1109/cyberc58899.2023.00034"},"language":"en","primary_location":{"id":"doi:10.1109/cyberc58899.2023.00034","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/cyberc58899.2023.00034","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery (CyberC)","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/A5100444183","display_name":"Yichi Zhang","orcid":"https://orcid.org/0000-0002-1780-7156"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yichi Zhang","raw_affiliation_strings":["Xi’an Jiaotong University,School of Computer Science and Technology,Xi’an,China"],"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,School of Computer Science and Technology,Xi’an,China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056067943","display_name":"Xinyu Yang","orcid":"https://orcid.org/0000-0001-5117-4914"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyu Yang","raw_affiliation_strings":["Xi’an Jiaotong University,School of Computer Science and Technology,Xi’an,China"],"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,School of Computer Science and Technology,Xi’an,China","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100444183"],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26032496,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"155","last_page":"158"},"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/T11309","display_name":"Music 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/T10860","display_name":"Speech and Audio Processing","score":0.9988999962806702,"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/emotion-recognition","display_name":"Emotion recognition","score":0.6736180782318115},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6415144801139832},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5871062278747559},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5776309967041016},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37592726945877075},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3251931667327881},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.11472553014755249}],"concepts":[{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.6736180782318115},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6415144801139832},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5871062278747559},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5776309967041016},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37592726945877075},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3251931667327881},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.11472553014755249},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cyberc58899.2023.00034","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/cyberc58899.2023.00034","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery (CyberC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5400000214576721,"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2146334809","https://openalex.org/W2148220354","https://openalex.org/W2191779130","https://openalex.org/W2533262878","https://openalex.org/W2892071465","https://openalex.org/W2914304175","https://openalex.org/W2966518489","https://openalex.org/W2972498864","https://openalex.org/W2972724712","https://openalex.org/W3015240477","https://openalex.org/W3015249983","https://openalex.org/W3015267357","https://openalex.org/W3015964358","https://openalex.org/W3163157357","https://openalex.org/W3177052299","https://openalex.org/W4223460604","https://openalex.org/W4293363567","https://openalex.org/W6729983426"],"related_works":["https://openalex.org/W1185300216","https://openalex.org/W2954163146","https://openalex.org/W2899086345","https://openalex.org/W2896057011","https://openalex.org/W3188962172","https://openalex.org/W2772917594","https://openalex.org/W4312825515","https://openalex.org/W3204019825","https://openalex.org/W3126677997","https://openalex.org/W1610857240"],"abstract_inverted_index":{"Speech":[0],"emotion":[1,78,86],"recognition":[2],"(SER)":[3],"is":[4],"an":[5],"indispensable":[6],"part":[7],"of":[8,83],"human":[9],"intention":[10],"understanding":[11],"in":[12],"human-computer":[13],"interaction":[14],"systems.":[15],"In":[16],"this":[17],"paper,":[18],"we":[19,69],"propose":[20,70],"a":[21,71],"novel":[22],"Blend-Sample":[23],"empowered":[24],"Global":[25,41],"&":[26,42],"Spectral":[27,43],"Attentive":[28,44],"(BS-GSA)":[29],"paradigm":[30,98],"for":[31,76],"more":[32],"robust":[33],"global":[34,48],"and":[35,49,65,80],"spectral":[36,66],"emotional":[37,60],"feature":[38],"learning.":[39],"The":[40],"(GSA)":[45],"model":[46,54],"captures":[47],"positional":[50],"information":[51],"with":[52],"attentive":[53],"design,":[55],"devotes":[56],"to":[57],"better":[58,81],"learning":[59,82],"representation":[61],"from":[62],"long-term":[63],"dependencies":[64],"characteristics.":[67],"Besides,":[68],"blend-sample":[72],"(BS)":[73],"augmentation":[74],"algorithm":[75],"equilibrated":[77],"samples":[79],"inconspicuous":[84],"frame-level":[85],"clues.":[87],"Experiments":[88],"conducted":[89],"on":[90],"the":[91,96],"IEMOCAP":[92],"dataset":[93],"demonstrate":[94],"that":[95],"proposed":[97],"outperforms":[99],"existing":[100],"methods,":[101],"reaching":[102],"state-of-the-art":[103],"performance.":[104]},"counts_by_year":[],"updated_date":"2025-12-21T23:12:01.093139","created_date":"2025-10-10T00:00:00"}