{"id":"https://openalex.org/W7130308521","doi":"https://doi.org/10.1109/o-cocosda68185.2025.11385088","title":"Neural Network-Based Speech Emotion Recognition for the Indonesian Language","display_name":"Neural Network-Based Speech Emotion Recognition for the Indonesian Language","publication_year":2025,"publication_date":"2025-11-12","ids":{"openalex":"https://openalex.org/W7130308521","doi":"https://doi.org/10.1109/o-cocosda68185.2025.11385088"},"language":null,"primary_location":{"id":"doi:10.1109/o-cocosda68185.2025.11385088","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda68185.2025.11385088","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 28th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","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":"https://openalex.org/A5126312561","display_name":"Muhammad Iqbal Asrif","orcid":null},"institutions":[{"id":"https://openalex.org/I29617571","display_name":"University of Indonesia","ror":"https://ror.org/0116zj450","country_code":"ID","type":"education","lineage":["https://openalex.org/I29617571"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Muhammad Iqbal Asrif","raw_affiliation_strings":["Universitas Indonesia,Faculty of Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universitas Indonesia,Faculty of Computer Science","institution_ids":["https://openalex.org/I29617571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126343688","display_name":"Muhammad Alif Ismady","orcid":null},"institutions":[{"id":"https://openalex.org/I29617571","display_name":"University of Indonesia","ror":"https://ror.org/0116zj450","country_code":"ID","type":"education","lineage":["https://openalex.org/I29617571"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Muhammad Alif Ismady","raw_affiliation_strings":["Universitas Indonesia,Faculty of Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universitas Indonesia,Faculty of Computer Science","institution_ids":["https://openalex.org/I29617571"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066073372","display_name":"Kurniawati Azizah","orcid":"https://orcid.org/0000-0002-3217-7025"},"institutions":[{"id":"https://openalex.org/I29617571","display_name":"University of Indonesia","ror":"https://ror.org/0116zj450","country_code":"ID","type":"education","lineage":["https://openalex.org/I29617571"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Kurniawati Azizah","raw_affiliation_strings":["Universitas Indonesia,Faculty of Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universitas Indonesia,Faculty of Computer Science","institution_ids":["https://openalex.org/I29617571"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I29617571"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.895799994468689,"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":0.895799994468689,"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/T11309","display_name":"Music and Audio Processing","score":0.029200000688433647,"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":0.025800000876188278,"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/indonesian","display_name":"Indonesian","score":0.6175000071525574},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.5673999786376953},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5327000021934509},{"id":"https://openalex.org/keywords/multilayer-perceptron","display_name":"Multilayer perceptron","score":0.4726000130176544},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4593999981880188},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4156999886035919},{"id":"https://openalex.org/keywords/emotion-classification","display_name":"Emotion classification","score":0.39480000734329224},{"id":"https://openalex.org/keywords/perceptron","display_name":"Perceptron","score":0.38679999113082886}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6456999778747559},{"id":"https://openalex.org/C2779207338","wikidata":"https://www.wikidata.org/wiki/Q9240","display_name":"Indonesian","level":2,"score":0.6175000071525574},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5834000110626221},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5673999786376953},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5327000021934509},{"id":"https://openalex.org/C179717631","wikidata":"https://www.wikidata.org/wiki/Q2991667","display_name":"Multilayer perceptron","level":3,"score":0.4726000130176544},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4593999981880188},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4496000111103058},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44769999384880066},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4156999886035919},{"id":"https://openalex.org/C206310091","wikidata":"https://www.wikidata.org/wiki/Q750859","display_name":"Emotion classification","level":2,"score":0.39480000734329224},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.38679999113082886},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.32839998602867126},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.29170000553131104},{"id":"https://openalex.org/C2781202465","wikidata":"https://www.wikidata.org/wiki/Q18346297","display_name":"Lexical diversity","level":3,"score":0.2809999883174896},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.2800000011920929},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2757999897003174},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.271699994802475},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.2676999866962433},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.26600000262260437},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.25920000672340393}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/o-cocosda68185.2025.11385088","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda68185.2025.11385088","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 28th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7349693179130554}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2009955221","https://openalex.org/W2064675550","https://openalex.org/W2092489135","https://openalex.org/W2136848157","https://openalex.org/W2143612262","https://openalex.org/W2146334809","https://openalex.org/W2148154194","https://openalex.org/W2919115771","https://openalex.org/W4404408300","https://openalex.org/W7128208329"],"related_works":[],"abstract_inverted_index":{"Speech":[0],"Emotion":[1],"Recognition":[2],"(SER)":[3],"plays":[4],"an":[5],"important":[6],"role":[7],"in":[8,31,58,77,107,126,136],"human-computer":[9],"interaction,":[10],"allowing":[11],"systems":[12],"to":[13,17,132],"detect":[14],"and":[15,44,49,90,95,117,147],"respond":[16],"human":[18],"emotions":[19],"from":[20],"voice":[21],"signals.":[22],"This":[23,129],"paper":[24],"presents":[25],"neural":[26,71],"network-based":[27],"models":[28],"for":[29,92,122],"SER":[30],"the":[32,64,81,85,93,96,102,108],"Indonesian":[33,127],"language.":[34],"We":[35,73],"implement":[36],"two":[37],"deep":[38],"learning":[39],"models,":[40,98],"Multi-Layer":[41],"Perceptron":[42],"(MLP)":[43],"Long":[45],"Short-Term":[46],"Memory":[47],"(LSTM)":[48],"explore":[50],"audio":[51],"feature":[52,105],"extraction":[53],"techniques.":[54],"To":[55],"overcome":[56],"challenges":[57,142],"low-resource":[59,137],"languages,":[60],"our":[61],"study":[62],"highlights":[63],"potential":[65],"of":[66,88,104],"combining":[67],"handcrafted":[68],"features":[69],"with":[70,144],"networks.":[72],"achieved":[74],"significant":[75],"advancements":[76],"emotion":[78,134],"classification":[79],"on":[80,101],"IndoWaveSentiment":[82],"dataset,":[83],"gaining":[84],"accuracy":[86],"values":[87],"71.7%":[89],"68.0%":[91],"MLP":[94,109],"LSTM":[97],"respectively.":[99],"Based":[100],"analysis":[103],"importance":[106],"model,":[110],"we":[111],"found":[112],"that":[113],"pitch":[114],"variability,":[115],"harmonics,":[116],"pause":[118],"duration":[119],"are":[120],"critical":[121],"distinguishing":[123],"emotional":[124],"expressions":[125],"speech.":[128],"research":[130],"contributes":[131],"improving":[133],"recognition":[135],"languages":[138],"like":[139],"Indonesian,":[140],"addressing":[141],"associated":[143],"linguistic":[145],"diversity":[146],"limited":[148],"annotated":[149],"datasets.":[150]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-02-19T00:00:00"}