{"id":"https://openalex.org/W4293778726","doi":"https://doi.org/10.3390/s22165941","title":"Effects of Data Augmentations on Speech Emotion Recognition","display_name":"Effects of Data Augmentations on Speech Emotion Recognition","publication_year":2022,"publication_date":"2022-08-09","ids":{"openalex":"https://openalex.org/W4293778726","doi":"https://doi.org/10.3390/s22165941","pmid":"https://pubmed.ncbi.nlm.nih.gov/36015717"},"language":"en","primary_location":{"id":"doi:10.3390/s22165941","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s22165941","pdf_url":"https://www.mdpi.com/1424-8220/22/16/5941/pdf?version=1660051472","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1424-8220/22/16/5941/pdf?version=1660051472","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065879041","display_name":"Bagus Tris Atmaja","orcid":"https://orcid.org/0000-0003-1560-2824"},"institutions":[{"id":"https://openalex.org/I166843116","display_name":"Sepuluh Nopember Institute of Technology","ror":"https://ror.org/05kbmmt89","country_code":"ID","type":"education","lineage":["https://openalex.org/I166843116"]},{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["ID","JP"],"is_corresponding":true,"raw_author_name":"Bagus Tris Atmaja","raw_affiliation_strings":["Institut Teknologi Sepuluh Nopember, Surabaya 60111, Indonesia","National Institute of Advanced Industrial Science and Technology, Tsukuba 305-8560, Japan"],"raw_orcid":"https://orcid.org/0000-0003-1560-2824","affiliations":[{"raw_affiliation_string":"Institut Teknologi Sepuluh Nopember, Surabaya 60111, Indonesia","institution_ids":["https://openalex.org/I166843116"]},{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology, Tsukuba 305-8560, Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046057045","display_name":"Akira Sasou","orcid":"https://orcid.org/0000-0003-1700-0325"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Akira Sasou","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology, Tsukuba 305-8560, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology, Tsukuba 305-8560, Japan","institution_ids":["https://openalex.org/I73613424"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5065879041"],"corresponding_institution_ids":["https://openalex.org/I166843116","https://openalex.org/I73613424"],"apc_list":{"value":2400,"currency":"CHF","value_usd":2598},"apc_paid":{"value":2400,"currency":"CHF","value_usd":2598},"fwci":6.1552,"has_fulltext":true,"cited_by_count":37,"citation_normalized_percentile":{"value":0.97006615,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"22","issue":"16","first_page":"5941","last_page":"5941"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9994999766349792,"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":0.9994000196456909,"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/speech-recognition","display_name":"Speech recognition","score":0.7535630464553833},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7453781366348267},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.7329266667366028},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4651418924331665},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4610637128353119},{"id":"https://openalex.org/keywords/silence","display_name":"Silence","score":0.46049100160598755},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4457206130027771}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7535630464553833},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7453781366348267},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.7329266667366028},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4651418924331665},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4610637128353119},{"id":"https://openalex.org/C2781115785","wikidata":"https://www.wikidata.org/wiki/Q502261","display_name":"Silence","level":2,"score":0.46049100160598755},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4457206130027771},{"id":"https://openalex.org/C107038049","wikidata":"https://www.wikidata.org/wiki/Q35986","display_name":"Aesthetics","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}],"mesh":[{"descriptor_ui":"D004644","descriptor_name":"Emotions","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004644","descriptor_name":"Emotions","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004644","descriptor_name":"Emotions","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004644","descriptor_name":"Emotions","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010465","descriptor_name":"Perception","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010465","descriptor_name":"Perception","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010465","descriptor_name":"Perception","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010465","descriptor_name":"Perception","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D060145","descriptor_name":"Text Messaging","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D060145","descriptor_name":"Text Messaging","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D060145","descriptor_name":"Text Messaging","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D060145","descriptor_name":"Text Messaging","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":5,"locations":[{"id":"doi:10.3390/s22165941","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s22165941","pdf_url":"https://www.mdpi.com/1424-8220/22/16/5941/pdf?version=1660051472","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},{"id":"pmid:36015717","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36015717","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors (Basel, Switzerland)","raw_type":null},{"id":"pmh:oai:doaj.org/article:09594440a1ae496b89c2b3ed80f75867","is_oa":true,"landing_page_url":"https://doaj.org/article/09594440a1ae496b89c2b3ed80f75867","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors, Vol 22, Iss 16, p 5941 (2022)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/1424-8220/22/16/5941/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/s22165941","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"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":"Sensors; Volume 22; Issue 16; Pages: 5941","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:9415521","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9415521","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"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":"Sensors (Basel)","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/s22165941","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s22165941","pdf_url":"https://www.mdpi.com/1424-8220/22/16/5941/pdf?version=1660051472","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6725152017","display_name":null,"funder_award_id":"JPNP20006","funder_id":"https://openalex.org/F4320321034","funder_display_name":"New Energy and Industrial Technology Development Organization"}],"funders":[{"id":"https://openalex.org/F4320321034","display_name":"New Energy and Industrial Technology Development Organization","ror":"https://ror.org/0055k7a87"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4293778726.pdf","grobid_xml":"https://content.openalex.org/works/W4293778726.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W1984327771","https://openalex.org/W1994295036","https://openalex.org/W2052666245","https://openalex.org/W2062207950","https://openalex.org/W2074788634","https://openalex.org/W2101234009","https://openalex.org/W2109138290","https://openalex.org/W2146334809","https://openalex.org/W2148220354","https://openalex.org/W2342475039","https://openalex.org/W2407080277","https://openalex.org/W2555915854","https://openalex.org/W2611652970","https://openalex.org/W2747664154","https://openalex.org/W2884270555","https://openalex.org/W2939274787","https://openalex.org/W2955758264","https://openalex.org/W2971275122","https://openalex.org/W2997399314","https://openalex.org/W3014919073","https://openalex.org/W3015988193","https://openalex.org/W3034669211","https://openalex.org/W3036601975","https://openalex.org/W3048645559","https://openalex.org/W3096723250","https://openalex.org/W3097488938","https://openalex.org/W3162538529","https://openalex.org/W3186192207","https://openalex.org/W3197580070","https://openalex.org/W3198086363","https://openalex.org/W3198126430","https://openalex.org/W3204696009","https://openalex.org/W3206252155","https://openalex.org/W4200054437","https://openalex.org/W4212956106","https://openalex.org/W4221089191","https://openalex.org/W4361994820","https://openalex.org/W6675354045","https://openalex.org/W6780218876","https://openalex.org/W6785045168"],"related_works":["https://openalex.org/W1491159402","https://openalex.org/W4297807400","https://openalex.org/W2249138175","https://openalex.org/W4313854686","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W289407349","https://openalex.org/W2368768466","https://openalex.org/W2757081366","https://openalex.org/W2640905660"],"abstract_inverted_index":{"Data":[0],"augmentation":[1,48,64,118,164],"techniques":[2],"have":[3],"recently":[4],"gained":[5],"more":[6,16,21,30,116,128],"adoption":[7],"in":[8,28,49,75],"speech":[9,12,50,72,87,134,153],"processing,":[10],"including":[11],"emotion":[13,51,73,135,154],"recognition.":[14,52],"Although":[15],"data":[17,31,47,63,69,99,117,123,129,147,163],"tend":[18,131],"to":[19,132,159],"be":[20,25],"effective,":[22],"there":[23],"may":[24],"a":[26,35,161,167],"trade-off":[27,142],"which":[29],"will":[32],"not":[33],"provide":[34],"better":[36],"model.":[37],"This":[38],"paper":[39],"reports":[40],"experiments":[41,79],"on":[42,82],"investigating":[43],"the":[44,58,66,83,109,121,141,144,150,157],"effects":[45],"of":[46,62,68,146,152],"The":[53,78,91,138],"investigation":[54],"aims":[55],"at":[56],"finding":[57],"most":[59],"useful":[60],"type":[61],"and":[65,88,105,126,149],"number":[67,145],"augmentations":[70,100,130,148],"for":[71,95,166],"recognition":[74,136,155],"various":[76],"conditions.":[77],"are":[80],"conducted":[81],"Japanese":[84],"Twitter-based":[85],"emotional":[86],"IEMOCAP":[89],"datasets.":[90],"results":[92,139],"show":[93],"that":[94],"speaker-independent":[96],"data,":[97],"two":[98],"with":[101,115],"glottal":[102],"source":[103],"extraction":[104],"silence":[106],"removal":[107],"exhibited":[108],"best":[110],"performance":[111,151],"among":[112],"others,":[113],"even":[114],"techniques.":[119],"For":[120],"text-independent":[122],"(including":[124],"speaker":[125],"text-independent),":[127],"improve":[133],"performances.":[137],"highlight":[140],"between":[143],"showing":[156],"necessity":[158],"choose":[160],"proper":[162],"technique":[165],"specific":[168],"condition.":[169]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":7}],"updated_date":"2026-06-12T08:23:45.883708","created_date":"2025-10-10T00:00:00"}
