{"id":"https://openalex.org/W2786121637","doi":"https://doi.org/10.1109/icspcs.2017.8270472","title":"Real time speech emotion recognition using RGB image classification and transfer learning","display_name":"Real time speech emotion recognition using RGB image classification and transfer learning","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2786121637","doi":"https://doi.org/10.1109/icspcs.2017.8270472","mag":"2786121637"},"language":"en","primary_location":{"id":"doi:10.1109/icspcs.2017.8270472","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icspcs.2017.8270472","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 11th International Conference on Signal Processing and Communication Systems (ICSPCS)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://figshare.com/articles/conference_contribution/Real_Time_Speech_Emotion_Recognition_Using_RGB_Image_Classification_and_Transfer_Learning/27582930","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055298907","display_name":"Melissa N. Stolar","orcid":"https://orcid.org/0000-0001-5193-3570"},"institutions":[{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Melissa N. Stolar","raw_affiliation_strings":["School of Engineering, RMIT University, Melbourne, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Engineering, RMIT University, Melbourne, Australia","institution_ids":["https://openalex.org/I82951845"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065207789","display_name":"Margaret Lech","orcid":"https://orcid.org/0000-0002-7860-7289"},"institutions":[{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Margaret Lech","raw_affiliation_strings":["School of Engineering, RMIT University, Melbourne, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Engineering, RMIT University, Melbourne, Australia","institution_ids":["https://openalex.org/I82951845"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046395470","display_name":"Robert S. Bolia","orcid":"https://orcid.org/0000-0002-9373-5772"},"institutions":[{"id":"https://openalex.org/I1303474014","display_name":"Defence Science and Technology Group","ror":"https://ror.org/05ddrvt52","country_code":"AU","type":"government","lineage":["https://openalex.org/I1303474014","https://openalex.org/I2801453606","https://openalex.org/I3139952251"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Robert S. Bolia","raw_affiliation_strings":["Aerospace Division, Defence Science and Technology (DST), Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aerospace Division, Defence Science and Technology (DST), Australia","institution_ids":["https://openalex.org/I1303474014"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103923116","display_name":"Michael Skinner","orcid":null},"institutions":[{"id":"https://openalex.org/I1303474014","display_name":"Defence Science and Technology Group","ror":"https://ror.org/05ddrvt52","country_code":"AU","type":"government","lineage":["https://openalex.org/I1303474014","https://openalex.org/I2801453606","https://openalex.org/I3139952251"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Michael Skinner","raw_affiliation_strings":["Aerospace Division, Defence Science and Technology (DST), Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aerospace Division, Defence Science and Technology (DST), Australia","institution_ids":["https://openalex.org/I1303474014"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.374,"has_fulltext":false,"cited_by_count":56,"citation_normalized_percentile":{"value":0.9035472,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9987999796867371,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9984999895095825,"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":0.8282367587089539},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.7280804514884949},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.697162926197052},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6945234537124634},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6512036323547363},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5685198903083801},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5008730888366699},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48385822772979736},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.47183018922805786},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.471443772315979},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4700813591480255},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.46662700176239014},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.45934754610061646},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.36334019899368286}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8282367587089539},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.7280804514884949},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.697162926197052},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6945234537124634},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6512036323547363},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5685198903083801},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5008730888366699},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48385822772979736},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.47183018922805786},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.471443772315979},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4700813591480255},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.46662700176239014},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.45934754610061646},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.36334019899368286}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icspcs.2017.8270472","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icspcs.2017.8270472","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 11th International Conference on Signal Processing and Communication Systems (ICSPCS)","raw_type":"proceedings-article"},{"id":"pmh:oai:alma.61RMIT_INST:11248107510001341","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ICSPCS.2017.8270472","pdf_url":null,"source":{"id":"https://openalex.org/S4306402074","display_name":"RMIT Research Repository (RMIT University Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I82951845","host_organization_name":"RMIT University","host_organization_lineage":["https://openalex.org/I82951845"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"pmh:oai:figshare.com:article/27582930","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Real_Time_Speech_Emotion_Recognition_Using_RGB_Image_Classification_and_Transfer_Learning/27582930","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference contribution"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/27582930","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Real_Time_Speech_Emotion_Recognition_Using_RGB_Image_Classification_and_Transfer_Learning/27582930","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference contribution"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7099999785423279,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320330929","display_name":"Trusted Autonomous Systems Defence CRC","ror":null},{"id":"https://openalex.org/F4320335334","display_name":"Defence Science and Technology Group","ror":null},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W175750906","https://openalex.org/W1501669607","https://openalex.org/W1528177290","https://openalex.org/W1602544193","https://openalex.org/W1663973292","https://openalex.org/W1849277567","https://openalex.org/W1945329967","https://openalex.org/W1968521648","https://openalex.org/W1970995885","https://openalex.org/W1973746598","https://openalex.org/W1999354778","https://openalex.org/W2025296793","https://openalex.org/W2028899742","https://openalex.org/W2036785409","https://openalex.org/W2055911634","https://openalex.org/W2060470614","https://openalex.org/W2066629172","https://openalex.org/W2087618018","https://openalex.org/W2095739681","https://openalex.org/W2097117768","https://openalex.org/W2113765418","https://openalex.org/W2114537326","https://openalex.org/W2117979998","https://openalex.org/W2132555391","https://openalex.org/W2137371678","https://openalex.org/W2146334809","https://openalex.org/W2147551994","https://openalex.org/W2153720647","https://openalex.org/W2155541015","https://openalex.org/W2158061940","https://openalex.org/W2159291411","https://openalex.org/W2163605009","https://openalex.org/W2168692779","https://openalex.org/W2194775991","https://openalex.org/W2281534628","https://openalex.org/W2295001676","https://openalex.org/W2296199791","https://openalex.org/W2492473494","https://openalex.org/W2516244654","https://openalex.org/W2578895956","https://openalex.org/W2593792475","https://openalex.org/W2598207902","https://openalex.org/W2602034649","https://openalex.org/W2919115771","https://openalex.org/W2951670162","https://openalex.org/W4212863985","https://openalex.org/W4294375521","https://openalex.org/W4300379313","https://openalex.org/W6630073874","https://openalex.org/W6640746083","https://openalex.org/W6684191040","https://openalex.org/W6734760474"],"related_works":["https://openalex.org/W2979740303","https://openalex.org/W3176438653","https://openalex.org/W2981628807","https://openalex.org/W4379875147","https://openalex.org/W3012393889","https://openalex.org/W2005234362","https://openalex.org/W3189091156","https://openalex.org/W3014041368","https://openalex.org/W2162970382","https://openalex.org/W1997235926"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"a":[3,36,48,74,106,131,154],"real-time":[4,170],"Speech":[5,78],"Emotion":[6],"Recognition":[7],"(SER)":[8],"task":[9],"formulated":[10],"as":[11,103],"an":[12,19,28],"image":[13,20,85],"classification":[14,21,86],"problem.":[15],"The":[16,96,140],"shift":[17],"to":[18,67,84,105,112,130,135,147,160],"paradigm":[22],"provided":[23],"the":[24,45,100,116,123,128,148,151,161,164],"advantage":[25],"of":[26,40,157,163],"using":[27],"existing":[29],"Deep":[30],"Neural":[31,109],"Network":[32,110],"(AlexNet)":[33,111],"pre-trained":[34,107],"on":[35,73],"very":[37],"large":[38],"number":[39,156],"images,":[41],"and":[42,59],"thus":[43],"eliminating":[44],"need":[46],"for":[47,115],"lengthy":[49],"network":[50,166],"training":[51,167],"process.":[52],"Two":[53],"alternative":[54],"multi-class":[55],"SER":[56],"systems,":[57],"AlexNet-SVM":[58,152],"FTAlexNet,":[60],"were":[61,65],"investigated.":[62],"Both":[63],"systems":[64],"shown":[66],"achieve":[68],"state-of-the-art":[69],"results":[70],"when":[71],"tested":[72],"popular":[75],"Berlin":[76],"Emotional":[77],"(EMO-DB)":[79],"database.":[80],"Transformation":[81],"from":[82],"speech":[83,94],"was":[87],"achieved":[88],"by":[89],"creating":[90],"RGB":[91],"images":[92,102,129],"depicting":[93],"spectrograms.":[95],"ALEXNet-SVM":[97],"method":[98,125],"passes":[99],"spectrogram":[101],"inputs":[104],"Convolutional":[108],"provide":[113,136],"features":[114],"Support":[117],"Vector":[118],"Machine":[119],"(SVM)":[120],"classifier,":[121],"whereas":[122],"FTAlexNet":[124,141],"simply":[126],"applies":[127],"fine":[132],"tuned":[133],"AlexNet":[134],"emotional":[137],"class":[138],"labels.":[139],"offers":[142],"slightly":[143],"higher":[144],"accuracy":[145],"compared":[146],"AlexNet-SVM,":[149],"while":[150],"requires":[153],"lower":[155],"computations":[158],"due":[159],"elimination":[162],"neural":[165],"procedure.":[168],"A":[169],"demo":[171],"is":[172],"given":[173],"on:":[174],"https://www.youtube.com/watch?v=fuMpF3cUqDU&t=6s.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":18},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":5}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}