{"id":"https://openalex.org/W2914424550","doi":"https://doi.org/10.1109/icspcs.2018.8631752","title":"Acoustic Characteristics of Emotional Speech Using Spectrogram Image Classification","display_name":"Acoustic Characteristics of Emotional Speech Using Spectrogram Image Classification","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2914424550","doi":"https://doi.org/10.1109/icspcs.2018.8631752","mag":"2914424550"},"language":"en","primary_location":{"id":"doi:10.1109/icspcs.2018.8631752","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icspcs.2018.8631752","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 12th 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/Acoustic_Characteristics_of_Emotional_Speech_Using_Spectrogram_Image_Classification/27583359","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/I4210095297","display_name":"MIT University","ror":"https://ror.org/00v140q16","country_code":"MK","type":"education","lineage":["https://openalex.org/I4210095297"]},{"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","MK"],"is_corresponding":false,"raw_author_name":"Melissa Stolar","raw_affiliation_strings":["RMIT University, Melbourne, VIC, AU"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RMIT University, Melbourne, VIC, AU","institution_ids":["https://openalex.org/I4210095297","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 Group, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aerospace Division, Defence Science and Technology Group, 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 Group, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aerospace Division, Defence Science and Technology Group, Australia","institution_ids":["https://openalex.org/I1303474014"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8813,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.86541957,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9980999827384949,"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":0.9955000281333923,"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/spectrogram","display_name":"Spectrogram","score":0.9196776151657104},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6966707706451416},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5868726968765259},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5817043781280518},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4663732647895813},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.42044925689697266},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4188099503517151},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3298283815383911}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.9196776151657104},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6966707706451416},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5868726968765259},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5817043781280518},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4663732647895813},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.42044925689697266},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4188099503517151},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3298283815383911}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icspcs.2018.8631752","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icspcs.2018.8631752","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 12th International Conference on Signal Processing and Communication Systems (ICSPCS)","raw_type":"proceedings-article"},{"id":"pmh:oai:alma.61RMIT_INST:11247620300001341","is_oa":false,"landing_page_url":"https://ieeexplore.ieee.org/abstract/document/8631752","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/27583359","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Acoustic_Characteristics_of_Emotional_Speech_Using_Spectrogram_Image_Classification/27583359","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/27583359","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Acoustic_Characteristics_of_Emotional_Speech_Using_Spectrogram_Image_Classification/27583359","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":[{"score":0.4399999976158142,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W175750906","https://openalex.org/W1501669607","https://openalex.org/W1552278919","https://openalex.org/W1603678007","https://openalex.org/W1971362524","https://openalex.org/W2005592325","https://openalex.org/W2008806652","https://openalex.org/W2013020033","https://openalex.org/W2032254851","https://openalex.org/W2055911634","https://openalex.org/W2087618018","https://openalex.org/W2111926505","https://openalex.org/W2114537326","https://openalex.org/W2118789253","https://openalex.org/W2123861288","https://openalex.org/W2125959970","https://openalex.org/W2137371678","https://openalex.org/W2137639365","https://openalex.org/W2148822124","https://openalex.org/W2150791533","https://openalex.org/W2296199791","https://openalex.org/W2317919972","https://openalex.org/W2325729322","https://openalex.org/W2578895956","https://openalex.org/W2580394854","https://openalex.org/W2598207902","https://openalex.org/W2602034649","https://openalex.org/W2625297138","https://openalex.org/W2786121637","https://openalex.org/W4245744384","https://openalex.org/W4248765999","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2897924318","https://openalex.org/W2138997758","https://openalex.org/W2184242386","https://openalex.org/W2325729322","https://openalex.org/W1923358586","https://openalex.org/W3126677997","https://openalex.org/W2981428355","https://openalex.org/W1834994814","https://openalex.org/W2041273198","https://openalex.org/W1599055764"],"abstract_inverted_index":{"One":[0],"of":[1,7,46,59,74,79,107,113,133],"the":[2,5,15,62,102,114],"problems":[3],"limiting":[4],"accuracy":[6],"speech":[8,48,60,75,134],"emotion":[9],"recognition":[10],"(SER)":[11],"is":[12,22,32],"difficulty":[13],"in":[14,28,61],"differentiation":[16],"between":[17,55,126],"acoustically-similar":[18],"emotions.":[19,99],"Since":[20],"it":[21,31],"not":[23],"clear":[24],"how":[25],"emotions":[26,128],"differ":[27],"acoustic":[29],"terms,":[30],"difficult":[33],"to":[34,51,90,97],"design":[35],"new,":[36],"more":[37],"efficient":[38],"SER":[39],"strategies.":[40],"In":[41],"this":[42],"study,":[43],"amplitude-frequency":[44,131],"analysis":[45,69],"emotional":[47,57],"was":[49],"performed":[50],"determine":[52],"relative":[53],"differences":[54],"seven":[56],"categories":[58],"Berlin":[63],"Emotional":[64],"Speech":[65],"(EMO-DB)":[66],"database.":[67],"The":[68,86],"transformed":[70],"short":[71],"1-second":[72],"blocks":[73],"into":[76],"RGB":[77,115],"images":[78,87,116],"spectrograms":[80],"using":[81],"four":[82],"different":[83,105,119,127],"frequency":[84,108,120],"scales.":[85],"were":[88,135],"used":[89],"train":[91],"a":[92],"convolutional":[93],"neural":[94],"network":[95,103],"(CNN)":[96],"recognize":[98],"By":[100],"training":[101],"with":[104],"combinations":[106],"scales":[109],"and":[110,121,129],"color":[111],"components":[112],"that":[117],"emphasized":[118],"spectral":[122],"amplitude":[123],"values,":[124],"links":[125],"corresponding":[130],"characteristics":[132],"determined.":[136]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":4}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}