{"id":"https://openalex.org/W4292955804","doi":"https://doi.org/10.48550/arxiv.2208.09830","title":"Representation Learning with Graph Neural Networks for Speech Emotion Recognition","display_name":"Representation Learning with Graph Neural Networks for Speech Emotion Recognition","publication_year":2022,"publication_date":"2022-08-21","ids":{"openalex":"https://openalex.org/W4292955804","doi":"https://doi.org/10.48550/arxiv.2208.09830"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2208.09830","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2208.09830","pdf_url":"https://arxiv.org/pdf/2208.09830","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2208.09830","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101459568","display_name":"Junghun Kim","orcid":"https://orcid.org/0000-0002-6118-1496","observed_orcids":["https://orcid.org/0000-0002-6118-1496","https://orcid.org/0000-0003-4607-5895"]},"institutions":[{"id":"https://openalex.org/I205490536","display_name":"Dongguk University","ror":"https://ror.org/057q6n778","country_code":"KR","type":"education","lineage":["https://openalex.org/I205490536"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kim, Junghun","raw_affiliation_strings":["Department of Artificial Intelligence , Dongguk University , Seoul , Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence , Dongguk University , Seoul , Korea","institution_ids":["https://openalex.org/I205490536"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080664764","display_name":"Jihie Kim","orcid":"https://orcid.org/0000-0003-2358-4021","observed_orcids":["https://orcid.org/0000-0003-2358-4021"]},"institutions":[{"id":"https://openalex.org/I205490536","display_name":"Dongguk University","ror":"https://ror.org/057q6n778","country_code":"KR","type":"education","lineage":["https://openalex.org/I205490536"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kim, Jihie","raw_affiliation_strings":["Department of Artificial Intelligence , Dongguk University , Seoul , Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence , Dongguk University , Seoul , Korea","institution_ids":["https://openalex.org/I205490536"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I205490536"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.986299991607666,"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"}},"topics":[{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.986299991607666,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.00559999980032444,"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"}},{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.002899999963119626,"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/speech-emotion-recognition","display_name":"speech emotion recognition","score":0.9990000128746033},{"id":"https://openalex.org/keywords/graph-neural-networks","display_name":"graph neural networks","score":0.9649999737739563},{"id":"https://openalex.org/keywords/graph-convolutional-networks","display_name":"graph convolutional networks","score":0.8460000157356262},{"id":"https://openalex.org/keywords/representation-learning","display_name":"representation learning","score":0.8220000267028809},{"id":"https://openalex.org/keywords/noise-robustness","display_name":"noise robustness","score":0.9229999780654907},{"id":"https://openalex.org/keywords/parameter-efficiency","display_name":"parameter efficiency","score":0.5210000276565552}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6636378765106201},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.6411452889442444},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5959477424621582},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5375828742980957},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5152552127838135},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.484493225812912},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.44004881381988525},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42648395895957947},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.41239333152770996},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4051515460014343},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2567688524723053},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2208.09830","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2208.09830","pdf_url":"https://arxiv.org/pdf/2208.09830","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2208.09830","doi":"https://doi.org/10.48550/arxiv.2208.09830","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2208.09830","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2208.09830","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2208.09830","pdf_url":"https://arxiv.org/pdf/2208.09830","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G4174933280","display_name":null,"funder_award_id":"IITP-2021-2020-0-01789","funder_id":"https://openalex.org/F4320324891","funder_display_name":"Iran Telecommunication Research Center"},{"id":"https://openalex.org/G6742338938","display_name":null,"funder_award_id":"IITP-2021-2020-0-01789","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G8310096245","display_name":null,"funder_award_id":"IITP\u20102021\u20102020\u20100\u201001789","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"}],"funders":[{"id":"https://openalex.org/F4320324891","display_name":"Iran Telecommunication Research Center","ror":"https://ror.org/01a3g2z22"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4292955804.pdf","grobid_xml":"https://content.openalex.org/works/W4292955804.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3047415206","https://openalex.org/W4391308001","https://openalex.org/W4412998503","https://openalex.org/W4387421847","https://openalex.org/W4398222647","https://openalex.org/W4229063381","https://openalex.org/W4407476451","https://openalex.org/W6996596625","https://openalex.org/W4392908930","https://openalex.org/W4283828626"],"abstract_inverted_index":{"Learning":[0],"expressive":[1,22],"representation":[2,23,44,67],"is":[3,81],"crucial":[4],"in":[5,17,69],"deep":[6],"learning.":[7,24],"In":[8,53],"speech":[9,19],"emotion":[10],"recognition":[11],"(SER),":[12],"vacuum":[13],"regions":[14],"or":[15,96],"noises":[16],"the":[18],"interfere":[20],"with":[21,100,106],"However,":[25],"traditional":[26],"RNN-based":[27],"models":[28],"are":[29],"susceptible":[30],"to":[31,83],"such":[32],"noise.":[33,86],"Recently,":[34],"Graph":[35,76],"Neural":[36],"Network":[37,78],"(GNN)":[38],"has":[39],"demonstrated":[40],"its":[41],"effectiveness":[42],"for":[43,51,66],"learning,":[45],"and":[46,85],"we":[47,55],"adopt":[48],"this":[49],"framework":[50],"SER.":[52,70],"particular,":[54],"propose":[56],"a":[57,73,101],"cosine":[58],"similarity-based":[59,75],"graph":[60,64],"as":[61],"an":[62],"ideal":[63],"structure":[65],"learning":[68],"We":[71],"present":[72],"Cosine":[74],"Convolutional":[77],"(CoGCN)":[79],"that":[80,90],"robust":[82],"perturbation":[84],"Experimental":[87],"results":[88,99],"show":[89],"our":[91],"method":[92],"outperforms":[93],"state-of-the-art":[94],"methods":[95],"provides":[97],"competitive":[98],"significant":[102],"model":[103],"size":[104],"reduction":[105],"only":[107],"1/30":[108],"parameters.":[109]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2022-08-24T00:00:00"}