{"id":"https://openalex.org/W4407691923","doi":"https://doi.org/10.1109/iceic64972.2025.10879629","title":"A Method for Improving the Accuracy of Speech Emotion Recognition Using Implicitly Filtered Image Generation in Extreme Noisy Environments","display_name":"A Method for Improving the Accuracy of Speech Emotion Recognition Using Implicitly Filtered Image Generation in Extreme Noisy Environments","publication_year":2025,"publication_date":"2025-01-19","ids":{"openalex":"https://openalex.org/W4407691923","doi":"https://doi.org/10.1109/iceic64972.2025.10879629"},"language":"en","primary_location":{"id":"doi:10.1109/iceic64972.2025.10879629","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iceic64972.2025.10879629","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Electronics, Information, and Communication (ICEIC)","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/A5091751755","display_name":"Jeong-Yoon Kim","orcid":"https://orcid.org/0009-0006-4525-7434"},"institutions":[{"id":"https://openalex.org/I145808223","display_name":"Hanbat National University","ror":"https://ror.org/00x514t95","country_code":"KR","type":"education","lineage":["https://openalex.org/I145808223"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Jeong-Yoon Kim","raw_affiliation_strings":["Hanbat National University,Department of Electronic Engineering,Daejeon,Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Hanbat National University,Department of Electronic Engineering,Daejeon,Republic of Korea","institution_ids":["https://openalex.org/I145808223"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100363400","display_name":"Seungho Lee","orcid":"https://orcid.org/0000-0002-4574-5511"},"institutions":[{"id":"https://openalex.org/I145808223","display_name":"Hanbat National University","ror":"https://ror.org/00x514t95","country_code":"KR","type":"education","lineage":["https://openalex.org/I145808223"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seung-Ho Lee","raw_affiliation_strings":["Hanbat National University,Department of Electronic Engineering,Daejeon,Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Hanbat National University,Department of Electronic Engineering,Daejeon,Republic of Korea","institution_ids":["https://openalex.org/I145808223"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5091751755"],"corresponding_institution_ids":["https://openalex.org/I145808223"],"apc_list":null,"apc_paid":null,"fwci":3.1486,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.89064929,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"3"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.7851999998092651,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.7851999998092651,"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/computer-science","display_name":"Computer science","score":0.7821913361549377},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7106494903564453},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.6772716045379639},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5061790347099304},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4974704086780548},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4168476462364197},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3275206387042999}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7821913361549377},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7106494903564453},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.6772716045379639},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5061790347099304},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4974704086780548},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4168476462364197},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3275206387042999}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iceic64972.2025.10879629","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iceic64972.2025.10879629","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Electronics, Information, and Communication (ICEIC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W2030931454","https://openalex.org/W2194775991","https://openalex.org/W3162293946","https://openalex.org/W4221153521","https://openalex.org/W4372346152"],"related_works":["https://openalex.org/W2755342338","https://openalex.org/W2779427294","https://openalex.org/W2775347418","https://openalex.org/W2625805835","https://openalex.org/W2079911747","https://openalex.org/W3116076068","https://openalex.org/W3003936178","https://openalex.org/W2145652935","https://openalex.org/W3126677997","https://openalex.org/W1610857240"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,144],"propose":[4],"a":[5,60,74,142,170,182],"method":[6,39,160,174],"to":[7,29,79],"improve":[8],"the":[9,23,30,34,44,54,86,90,101,106,130,134,146,152,165,172,186],"accuracy":[10,177,190],"of":[11,33,129,138,148,154,178,191],"speech":[12,24,35,55,97,192],"emotion":[13,98,193],"recognition":[14,99,194],"in":[15,43],"extreme":[16],"situations":[17],"where":[18],"noise":[19,50,149],"is":[20,27,40,51,114,161,181],"injected":[21,52],"into":[22,53,59],"signal,":[25],"which":[26,113,180],"equivalent":[28],"signal":[31,56],"magnitude":[32],"signal.":[36],"The":[37,158],"proposed":[38,159,173],"carried":[41],"out":[42],"following":[45],"steps.":[46],"i:":[47],"Random":[48],"Gaussian":[49],"and":[57,73,150,188],"converted":[58],"log-Mel":[61,92],"spectrogram":[62,93,117],"image":[63,84,104,118,136],"by":[64,124],"performing":[65],"short-term":[66],"Fourier":[67],"transform":[68],"(STFT),":[69],"etc.":[70],"ii:":[71],"ResNet50":[72],"deconvolution":[75],"layer":[76],"are":[77],"used":[78],"generate":[80],"an":[81,176],"implicitly":[82,102,126],"filtered":[83,103,127],"with":[85],"same":[87,131],"size":[88,132],"as":[89,133],"input":[91,135],"image.":[94],"iii:":[95],"Perform":[96],"from":[100],"using":[105,141,164,195],"vertically":[107],"long":[108],"patch":[109],"vision":[110],"transformer":[111],"(ViT),":[112],"excellent":[115],"for":[116],"analysis.":[119],"We":[120],"experimentally":[121],"demonstrate":[122],"that":[123],"generating":[125],"images":[128],"instead":[137],"conventional":[139],"filtering":[140],"CNN,":[143],"minimise":[145],"intervention":[147],"facilitate":[151],"detection":[153],"high":[155],"importance":[156],"features.":[157],"objectively":[162],"evaluated":[163],"noise-injected":[166],"CREMA-D":[167],"dataset.":[168],"As":[169],"result,":[171],"achieves":[175],"39.02%,":[179],"significant":[183],"improvement":[184],"over":[185],"11.95%":[187],"17.66%":[189],"existing":[196],"methods.":[197]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}