{"id":"https://openalex.org/W4385299257","doi":"https://doi.org/10.1145/3603781.3603919","title":"Speech emotion recognition algorithm based on bimodality and attention mechanism","display_name":"Speech emotion recognition algorithm based on bimodality and attention mechanism","publication_year":2023,"publication_date":"2023-05-26","ids":{"openalex":"https://openalex.org/W4385299257","doi":"https://doi.org/10.1145/3603781.3603919"},"language":"en","primary_location":{"id":"doi:10.1145/3603781.3603919","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3603781.3603919","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 4th International Conference on Computing, Networks and Internet of Things","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/A5083729144","display_name":"Huangshui Hu","orcid":"https://orcid.org/0000-0003-2545-3420"},"institutions":[{"id":"https://openalex.org/I4385474403","display_name":"Changchun University of Technology","ror":"https://ror.org/052pakb34","country_code":null,"type":"education","lineage":["https://openalex.org/I4385474403"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Huangshui Hu","raw_affiliation_strings":["Changchun University of Technology, China"],"affiliations":[{"raw_affiliation_string":"Changchun University of Technology, China","institution_ids":["https://openalex.org/I4385474403","https://openalex.org/I4385474403"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103074021","display_name":"Hongyu Sun","orcid":"https://orcid.org/0009-0000-2478-0062"},"institutions":[{"id":"https://openalex.org/I4385474403","display_name":"Changchun University of Technology","ror":"https://ror.org/052pakb34","country_code":null,"type":"education","lineage":["https://openalex.org/I4385474403"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongyu Sun","raw_affiliation_strings":["Changchun University of Technology, China"],"affiliations":[{"raw_affiliation_string":"Changchun University of Technology, China","institution_ids":["https://openalex.org/I4385474403","https://openalex.org/I4385474403"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102987029","display_name":"Peisong Xie","orcid":"https://orcid.org/0009-0001-6881-7602"},"institutions":[{"id":"https://openalex.org/I4385474403","display_name":"Changchun University of Technology","ror":"https://ror.org/052pakb34","country_code":null,"type":"education","lineage":["https://openalex.org/I4385474403"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peisong Xie","raw_affiliation_strings":["Changchun University of Technology, China"],"affiliations":[{"raw_affiliation_string":"Changchun University of Technology, China","institution_ids":["https://openalex.org/I4385474403","https://openalex.org/I4385474403"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101985966","display_name":"Nanhao Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I4385474403","display_name":"Changchun University of Technology","ror":"https://ror.org/052pakb34","country_code":null,"type":"education","lineage":["https://openalex.org/I4385474403"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nanhao Shen","raw_affiliation_strings":["Changchun University of Technology, China"],"affiliations":[{"raw_affiliation_string":"Changchun University of Technology, China","institution_ids":["https://openalex.org/I4385474403","https://openalex.org/I4385474403"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101756517","display_name":"Mei Han","orcid":"https://orcid.org/0009-0001-4493-2593"},"institutions":[{"id":"https://openalex.org/I4385474403","display_name":"Changchun University of Technology","ror":"https://ror.org/052pakb34","country_code":null,"type":"education","lineage":["https://openalex.org/I4385474403"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mei Han","raw_affiliation_strings":["Changchun University of Technology, China"],"affiliations":[{"raw_affiliation_string":"Changchun University of Technology, China","institution_ids":["https://openalex.org/I4385474403","https://openalex.org/I4385474403"]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5083729144"],"corresponding_institution_ids":["https://openalex.org/I4385474403"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11559154,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"776","last_page":"781"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9965000152587891,"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":0.9965000152587891,"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":0.9642999768257141,"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/T12260","display_name":"Educational Technology and Pedagogy","score":0.9473000168800354,"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/spectrogram","display_name":"Spectrogram","score":0.7957351803779602},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7805721759796143},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.5909292697906494},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5669406056404114},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5580487847328186},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5407950282096863},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5024549961090088},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.44035103917121887},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4324858486652374},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4220128059387207}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7957351803779602},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7805721759796143},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5909292697906494},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5669406056404114},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5580487847328186},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5407950282096863},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5024549961090088},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.44035103917121887},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4324858486652374},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4220128059387207},{"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:10.1145/3603781.3603919","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3603781.3603919","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 4th International Conference on Computing, Networks and Internet of Things","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5299999713897705,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1981276685","https://openalex.org/W2161073241","https://openalex.org/W2965453734","https://openalex.org/W2986661129","https://openalex.org/W3132302778","https://openalex.org/W3183891373","https://openalex.org/W4281701185","https://openalex.org/W4286908330","https://openalex.org/W6600360367","https://openalex.org/W6601365666","https://openalex.org/W6609196980"],"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/W2184242386","https://openalex.org/W2325729322","https://openalex.org/W1923358586"],"abstract_inverted_index":{"To":[0],"address":[1],"the":[2,25,67,82,90,100],"problem":[3],"of":[4,7,77],"low":[5],"accuracy":[6],"unimodal":[8],"speech":[9,16],"emotion":[10,17],"recognition":[11,18],"methods,":[12],"a":[13,35],"bimodal":[14,36],"MCNN-BiLSTM-Attention":[15],"algorithm":[19,23,37,71],"is":[20],"proposed.":[21],"The":[22,70],"adopts":[24],"Mel-spectrogram":[26],"and":[27,47,50,56,62,74,79,85,87],"text":[28],"information":[29],"in":[30],"audio":[31],"as":[32],"input,":[33],"constructs":[34],"with":[38,99],"attention":[39],"mechanism":[40],"based":[41],"on":[42,81,89],"convolutional":[43],"neural":[44],"network":[45,53],"CNN":[46],"bi-directional":[48],"long":[49],"short-term":[51],"memory":[52],"BiLSTM,":[54],"respectively,":[55,93],"uses":[57],"Early":[58],"fusion,":[59],"Feature":[60],"fusion":[61],"data":[63],"augmentation":[64],"to":[65],"improve":[66],"classification":[68],"accuracy.":[69],"achieves":[72],"WA":[73],"UA":[75],"accuracies":[76],"74.10%":[78],"77.10%":[80],"IEMOCAP":[83],"dataset":[84],"59.90%":[86],"52.80%":[88],"MELD":[91],"dataset,":[92],"which":[94],"are":[95],"significantly":[96],"improved":[97],"compared":[98],"single-modal":[101],"approach.":[102]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}