{"id":"https://openalex.org/W4200043683","doi":"https://doi.org/10.1109/ispacs51563.2021.9651089","title":"Comparative Analysis of Features In a Speech Emotion Recognition System using Convolutional Neural Networks","display_name":"Comparative Analysis of Features In a Speech Emotion Recognition System using Convolutional Neural Networks","publication_year":2021,"publication_date":"2021-11-16","ids":{"openalex":"https://openalex.org/W4200043683","doi":"https://doi.org/10.1109/ispacs51563.2021.9651089"},"language":"en","primary_location":{"id":"doi:10.1109/ispacs51563.2021.9651089","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ispacs51563.2021.9651089","pdf_url":null,"source":{"id":"https://openalex.org/S4363605678","display_name":"2021 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)","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/A5022399379","display_name":"P.Sirish Kumar","orcid":null},"institutions":[{"id":"https://openalex.org/I4389425378","display_name":"R.V. College of Engineering","ror":"https://ror.org/041re0e60","country_code":null,"type":"education","lineage":["https://openalex.org/I4389425378"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Prachii Kumar","raw_affiliation_strings":["Dept. of Electronics and Communication Engineering, R.V. College of Engineering, Bangalore, India"],"affiliations":[{"raw_affiliation_string":"Dept. of Electronics and Communication Engineering, R.V. College of Engineering, Bangalore, India","institution_ids":["https://openalex.org/I4389425378"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082763839","display_name":"K S Shushrutha","orcid":null},"institutions":[{"id":"https://openalex.org/I4389425378","display_name":"R.V. College of Engineering","ror":"https://ror.org/041re0e60","country_code":null,"type":"education","lineage":["https://openalex.org/I4389425378"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"K. S. Shushrutha","raw_affiliation_strings":["Dept. of Electronics and Communication Engineering, R.V. College of Engineering, Bangalore, India"],"affiliations":[{"raw_affiliation_string":"Dept. of Electronics and Communication Engineering, R.V. College of Engineering, Bangalore, India","institution_ids":["https://openalex.org/I4389425378"]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5022399379"],"corresponding_institution_ids":["https://openalex.org/I4389425378"],"apc_list":null,"apc_paid":null,"fwci":0.3441,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.53928811,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"44","issue":null,"first_page":"1","last_page":"2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.9958000183105469,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8518275618553162},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.8412437438964844},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7693204879760742},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.7683284282684326},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7433485388755798},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5739850997924805},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5186528563499451},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.505207359790802},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.48968270421028137},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.44242334365844727},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4397156238555908},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4233304560184479}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8518275618553162},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.8412437438964844},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7693204879760742},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7683284282684326},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7433485388755798},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5739850997924805},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5186528563499451},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.505207359790802},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.48968270421028137},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.44242334365844727},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4397156238555908},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4233304560184479},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","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:10.1109/ispacs51563.2021.9651089","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ispacs51563.2021.9651089","pdf_url":null,"source":{"id":"https://openalex.org/S4363605678","display_name":"2021 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)","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":6,"referenced_works":["https://openalex.org/W2074788634","https://openalex.org/W2793383796","https://openalex.org/W2899201823","https://openalex.org/W2949471033","https://openalex.org/W3008039831","https://openalex.org/W6763271673"],"related_works":["https://openalex.org/W4252379076","https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W4385672897","https://openalex.org/W2373675101","https://openalex.org/W106160982","https://openalex.org/W2359140082","https://openalex.org/W1556565948","https://openalex.org/W4317383455"],"abstract_inverted_index":{"In":[0,70],"the":[1,43,66,74,77,99,112,124,131,136],"past":[2],"decade,":[3],"Speech":[4,105],"Emotion":[5],"Recognition":[6],"(SER)":[7],"in":[8,38,42,65,115],"many":[9],"spoken":[10],"languages":[11],"has":[12,60],"become":[13],"a":[14,35,46,89],"field":[15],"of":[16,45,68,76,103,121],"growing":[17],"interest.":[18],"MFCCs":[19,64,137],"(Mel":[20],"Frequency":[21],"Cepstrum":[22],"Coefficients)":[23],"are":[24,32],"commonly":[25],"utilized":[26],"representations":[27],"for":[28,123,130],"audio":[29],"classification,":[30],"and":[31,79,106,140],"now":[33],"becoming":[34],"prominent":[36],"feature":[37,52],"SER":[39],"systems.":[40],"However,":[41],"view":[44],"performance":[47],"analysis,":[48],"there":[49],"exists":[50],"another":[51],"named":[53],"PCEN":[54],"(Per":[55],"Channel":[56],"Energy":[57],"Normalization)":[58],"that":[59,126,133,142],"proven":[61],"to":[62,72],"outperform":[63],"context":[67],"speech.":[69],"order":[71],"compare":[73],"performances":[75],"MFCC":[78],"PCEN,":[80,128],"they":[81],"have":[82],"individually":[83],"been":[84],"used":[85],"as":[86,138],"inputs":[87],"into":[88],"one":[90],"dimensional":[91],"Convolutional":[92],"Neural":[93],"Network":[94],"(CNN).":[95],"The":[96],"samples":[97],"from":[98],"Ryerson":[100],"Audio-Visual":[101],"Database":[102],"Emotional":[104],"Song":[107],"(RAVDESS)":[108],"were":[109],"utilized.":[110],"Furthermore,":[111],"framework":[113],"proposed":[114],"this":[116],"paper":[117],"obtains":[118],"an":[119],"accuracy":[120],"85.3%":[122],"configuration":[125,132],"utilizes":[127],"77.4%":[129],"uses":[134],"only":[135],"inputs,":[139],"78.1%":[141],"combines":[143],"both.":[144]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}