{"id":"https://openalex.org/W4391308001","doi":"https://doi.org/10.1109/icspcc59353.2023.10400357","title":"Speech Emotion Recognition Based on Feature Fusion and Residual Graph Convolutional Network","display_name":"Speech Emotion Recognition Based on Feature Fusion and Residual Graph Convolutional Network","publication_year":2023,"publication_date":"2023-11-14","ids":{"openalex":"https://openalex.org/W4391308001","doi":"https://doi.org/10.1109/icspcc59353.2023.10400357"},"language":"en","primary_location":{"id":"doi:10.1109/icspcc59353.2023.10400357","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icspcc59353.2023.10400357","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC)","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/A5103221053","display_name":"Yuanbang Zhang","orcid":"https://orcid.org/0009-0009-1400-2676"},"institutions":[{"id":"https://openalex.org/I27599042","display_name":"Xi'an Polytechnic University","ror":"https://ror.org/03442p831","country_code":"CN","type":"education","lineage":["https://openalex.org/I27599042"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuanbang Zhang","raw_affiliation_strings":["School of Electronics and Information, Xi'an Polytechnic University,Xi'an,China"],"affiliations":[{"raw_affiliation_string":"School of Electronics and Information, Xi'an Polytechnic University,Xi'an,China","institution_ids":["https://openalex.org/I27599042"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101722153","display_name":"Lin Cui","orcid":"https://orcid.org/0000-0003-1523-9885"},"institutions":[{"id":"https://openalex.org/I27599042","display_name":"Xi'an Polytechnic University","ror":"https://ror.org/03442p831","country_code":"CN","type":"education","lineage":["https://openalex.org/I27599042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Cui","raw_affiliation_strings":["School of Electronics and Information, Xi'an Polytechnic University,Xi'an,China"],"affiliations":[{"raw_affiliation_string":"School of Electronics and Information, Xi'an Polytechnic University,Xi'an,China","institution_ids":["https://openalex.org/I27599042"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065615188","display_name":"Xiaodong Sun","orcid":"https://orcid.org/0000-0001-7775-2823"},"institutions":[{"id":"https://openalex.org/I27599042","display_name":"Xi'an Polytechnic University","ror":"https://ror.org/03442p831","country_code":"CN","type":"education","lineage":["https://openalex.org/I27599042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaodong Sun","raw_affiliation_strings":["School of Electronics and Information, Xi'an Polytechnic University,Xi'an,China"],"affiliations":[{"raw_affiliation_string":"School of Electronics and Information, Xi'an Polytechnic University,Xi'an,China","institution_ids":["https://openalex.org/I27599042"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027659333","display_name":"Kai Xue","orcid":"https://orcid.org/0009-0001-4866-8646"},"institutions":[{"id":"https://openalex.org/I27599042","display_name":"Xi'an Polytechnic University","ror":"https://ror.org/03442p831","country_code":"CN","type":"education","lineage":["https://openalex.org/I27599042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Xue","raw_affiliation_strings":["School of Electronics and Information, Xi'an Polytechnic University,Xi'an,China"],"affiliations":[{"raw_affiliation_string":"School of Electronics and Information, Xi'an Polytechnic University,Xi'an,China","institution_ids":["https://openalex.org/I27599042"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5103221053"],"corresponding_institution_ids":["https://openalex.org/I27599042"],"apc_list":null,"apc_paid":null,"fwci":0.2612,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.63077383,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"56","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9988999962806702,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9972000122070312,"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/residual","display_name":"Residual","score":0.7601000070571899},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7408095598220825},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.6823606491088867},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6712837219238281},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6035797595977783},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5935683250427246},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5886062383651733},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5838534235954285},{"id":"https://openalex.org/keywords/convolutional-code","display_name":"Convolutional code","score":0.4576645493507385},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4446033835411072},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.43440741300582886},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.43116217851638794},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.42334768176078796},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2669779360294342},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.22194316983222961},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.09583145380020142}],"concepts":[{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.7601000070571899},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7408095598220825},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.6823606491088867},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6712837219238281},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6035797595977783},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5935683250427246},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5886062383651733},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5838534235954285},{"id":"https://openalex.org/C157899210","wikidata":"https://www.wikidata.org/wiki/Q1395022","display_name":"Convolutional code","level":3,"score":0.4576645493507385},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4446033835411072},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.43440741300582886},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.43116217851638794},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.42334768176078796},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2669779360294342},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.22194316983222961},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.09583145380020142},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icspcc59353.2023.10400357","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icspcc59353.2023.10400357","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2790404832","https://openalex.org/W2806051338","https://openalex.org/W2884585870","https://openalex.org/W2915402499","https://openalex.org/W2919464470","https://openalex.org/W2954137266","https://openalex.org/W2962946486","https://openalex.org/W2963076818","https://openalex.org/W2973181312","https://openalex.org/W2985882473","https://openalex.org/W2990045899","https://openalex.org/W3002872170","https://openalex.org/W3008039831","https://openalex.org/W3022013598","https://openalex.org/W3038985617","https://openalex.org/W3094378471","https://openalex.org/W3162024001","https://openalex.org/W3162387328","https://openalex.org/W3162475537","https://openalex.org/W3173396651","https://openalex.org/W4285293277","https://openalex.org/W4292955804","https://openalex.org/W4300273322","https://openalex.org/W4379230561","https://openalex.org/W6726873649","https://openalex.org/W6842013374"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W4402568167","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W3127543252","https://openalex.org/W2065606036","https://openalex.org/W2942893872"],"abstract_inverted_index":{"Applying":[0],"Graph":[1],"Convolutional":[2,50],"Networks":[3],"(GCN)":[4],"to":[5,57],"Speech":[6],"Emotion":[7],"Recognition":[8],"(SER)":[9],"tasks":[10],"is":[11,55,67],"a":[12,81,90],"novel":[13],"idea,":[14],"but":[15],"the":[16,24,43,63,75,98,105,108],"selection":[17],"of":[18,23,107,114],"effective":[19],"features":[20,38,77],"and":[21,41,62,87,101,117],"deepening":[22],"GCN":[25],"layers":[26],"remain":[27],"unresolved":[28],"issues.":[29],"To":[30],"address":[31],"this,":[32],"this":[33],"paper":[34],"uses":[35],"two":[36],"acoustic":[37],"as":[39],"inputs":[40],"improves":[42],"model":[44],"structure.":[45],"Firstly,":[46],"AlexNet":[47],"that":[48],"integrates":[49],"Block":[51],"Attention":[52],"Module":[53],"(CBAM)":[54],"used":[56],"extract":[58],"log":[59],"Mel-spectrogram":[60],"features,":[61],"CBAM":[64],"attention":[65],"output":[66],"concatenated":[68,76],"with":[69,111],"Mel-frequency":[70],"cepstral":[71],"coefficients":[72],"(MFCC).":[73],"Then,":[74],"are":[78],"input":[79],"into":[80],"4-layer":[82],"residual":[83],"graph":[84],"convolutional":[85],"network":[86],"followed":[88],"by":[89],"fully":[91],"connected":[92],"classification":[93],"layer.":[94],"Experimental":[95],"results":[96],"on":[97],"CASIA,":[99],"RAVDESS,":[100],"IEMOCAP":[102],"datasets":[103],"demonstrate":[104],"superiority":[106],"proposed":[109],"method":[110],"weighted":[112],"accuracies":[113],"92.2%,":[115],"79.8%,":[116],"70.1":[118],"%":[119],"respectively.":[120]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-25T23:11:45.687758","created_date":"2025-10-10T00:00:00"}