{"id":"https://openalex.org/W4206322605","doi":"https://doi.org/10.23919/eusipco54536.2021.9616144","title":"Speech Emotion Recognition Using Auditory Spectrogram and Cepstral Features","display_name":"Speech Emotion Recognition Using Auditory Spectrogram and Cepstral Features","publication_year":2021,"publication_date":"2021-08-23","ids":{"openalex":"https://openalex.org/W4206322605","doi":"https://doi.org/10.23919/eusipco54536.2021.9616144"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco54536.2021.9616144","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9616144","pdf_url":null,"source":{"id":"https://openalex.org/S4363607854","display_name":"2021 29th European Signal Processing Conference (EUSIPCO)","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 29th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"},"type":"conference-paper","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":null,"display_name":"Shujie Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shujie Zhao","raw_affiliation_strings":["CIAIC, Northwestern Polytechnical University, Xi'an, China","CIAIC, Northwestern Polytechnical University, Xi&#x0027","an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CIAIC, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"CIAIC, Northwestern Polytechnical University, Xi&#x0027","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"an, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100318832","display_name":"Yang Yan","orcid":"https://orcid.org/0000-0001-7694-2801"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Yang","raw_affiliation_strings":["CIAIC, Northwestern Polytechnical University, Xi'an, China","CIAIC, Northwestern Polytechnical University, Xi&#x0027","an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CIAIC, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"CIAIC, Northwestern Polytechnical University, Xi&#x0027","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"an, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080194185","display_name":"Israel Cohen","orcid":"https://orcid.org/0000-0002-2556-3972"},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Israel Cohen","raw_affiliation_strings":["Technion-Israel Institute of Technology, Haifa, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technion-Israel Institute of Technology, Haifa, Israel","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101518452","display_name":"Lijun Zhang","orcid":"https://orcid.org/0000-0002-9453-4032"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lijun Zhang","raw_affiliation_strings":["CIAIC, Northwestern Polytechnical University, Xi'an, China","CIAIC, Northwestern Polytechnical University, Xi&#x0027","an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CIAIC, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"CIAIC, Northwestern Polytechnical University, Xi&#x0027","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"an, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3626,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.56405301,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"136","last_page":"140"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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":0.9994000196456909,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987000226974487,"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/spectrogram","display_name":"Spectrogram","score":0.900037944316864},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.8152003288269043},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7919460535049438},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.751075029373169},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7153503894805908},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6721692681312561},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5180304646492004},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44290733337402344},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.43923521041870117},{"id":"https://openalex.org/keywords/environmental-noise","display_name":"Environmental noise","score":0.4306687116622925},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4056616425514221},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.12441980838775635},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.05984655022621155}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.900037944316864},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.8152003288269043},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7919460535049438},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.751075029373169},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7153503894805908},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6721692681312561},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5180304646492004},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44290733337402344},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.43923521041870117},{"id":"https://openalex.org/C86781634","wikidata":"https://www.wikidata.org/wiki/Q2478325","display_name":"Environmental noise","level":3,"score":0.4306687116622925},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4056616425514221},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.12441980838775635},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.05984655022621155},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/eusipco54536.2021.9616144","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9616144","pdf_url":null,"source":{"id":"https://openalex.org/S4363607854","display_name":"2021 29th European Signal Processing Conference (EUSIPCO)","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 29th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5099999904632568,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G4734082079","display_name":null,"funder_award_id":"6177012290,F011305","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W18651926","https://openalex.org/W175750906","https://openalex.org/W1966359074","https://openalex.org/W1996734935","https://openalex.org/W2061140267","https://openalex.org/W2103869314","https://openalex.org/W2144264893","https://openalex.org/W2147634797","https://openalex.org/W2148154194","https://openalex.org/W2171903461","https://openalex.org/W2214686774","https://openalex.org/W2220007491","https://openalex.org/W2304515954","https://openalex.org/W2395913652","https://openalex.org/W2403254325","https://openalex.org/W2525246137","https://openalex.org/W2562383591","https://openalex.org/W2790234617","https://openalex.org/W2810490977","https://openalex.org/W2902806526","https://openalex.org/W2908073754","https://openalex.org/W2915189764","https://openalex.org/W2981416151","https://openalex.org/W3023830767","https://openalex.org/W3048835987","https://openalex.org/W3087957214","https://openalex.org/W3118765838","https://openalex.org/W3162047160","https://openalex.org/W6688746279","https://openalex.org/W6688910204","https://openalex.org/W6713238902"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W2787035864","https://openalex.org/W2373675101","https://openalex.org/W4385672897","https://openalex.org/W106160982","https://openalex.org/W2359140082","https://openalex.org/W2074132948","https://openalex.org/W2160511961"],"abstract_inverted_index":{"A":[0],"systematic":[1],"comparison":[2],"on":[3,9,49,65,127],"the":[4,33,45,59,86,97,124,128],"impact":[5],"of":[6,35,78,131,139],"environmental":[7],"noises":[8],"key":[10],"acoustic":[11,37],"features":[12,38,100,126,151,154],"is":[13],"critical":[14],"in":[15,39,161],"order":[16],"to":[17,74,94],"transfer":[18],"speech":[19,51,55,133],"emotion":[20],"recognition":[21,104],"(SER)":[22],"systems":[23],"into":[24],"real":[25],"world":[26],"applications.":[27,163],"In":[28],"this":[29],"study,":[30],"we":[31],"investigate":[32],"noise-tolerance":[34],"different":[36],"distinguishing":[40],"various":[41],"emotions":[42,79],"by":[43],"comparing":[44],"SER":[46,156],"classification":[47],"performance":[48],"clean":[50,87],"signals":[52],"and":[53,61,69,88,152],"noisy":[54,89],"signals.":[56],"We":[57],"extract":[58],"spectrum":[60],"cepstral":[62,95,119,153],"parameters":[63],"based":[64],"human":[66],"auditory":[67,98,149],"characteristics":[68],"develop":[70],"machine":[71],"learning":[72],"algorithms":[73],"classify":[75],"four":[76,137],"types":[77],"using":[80],"these":[81],"features.":[82],"Experimental":[83],"results":[84,144],"across":[85],"data":[90],"show":[91,145],"that":[92],"compared":[93],"features,":[96],"spectrogram-based":[99,150],"can":[101],"achieve":[102],"higher":[103],"accuracy":[105,113],"for":[106,114,155],"low":[107],"signal-to-noise":[108],"ratios":[109],"(SNRs),":[110],"but":[111],"lower":[112],"high":[115],"SNRs.":[116],"Gammatone":[117],"filter":[118],"coefficients":[120],"(GFCCs)":[121],"outperformed":[122],"all":[123,136],"extracted":[125],"Berlin":[129],"database":[130],"emotional":[132],"(EmoDB),":[134],"under":[135],"kinds":[138],"tested":[140],"noise":[141,159],"conditions.":[142],"These":[143],"compensation":[146],"relationships":[147],"between":[148],"with":[157],"better":[158],"robustness":[160],"real-world":[162]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}