{"id":"https://openalex.org/W2900168190","doi":"https://doi.org/10.1109/iwaenc.2018.8521333","title":"Convolutional Neural Network Techniques for Speech Emotion Recognition","display_name":"Convolutional Neural Network Techniques for Speech Emotion Recognition","publication_year":2018,"publication_date":"2018-09-01","ids":{"openalex":"https://openalex.org/W2900168190","doi":"https://doi.org/10.1109/iwaenc.2018.8521333","mag":"2900168190"},"language":"en","primary_location":{"id":"doi:10.1109/iwaenc.2018.8521333","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwaenc.2018.8521333","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 16th International Workshop on Acoustic Signal Enhancement (IWAENC)","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/A5103091951","display_name":"Srinivas Parthasarathy","orcid":"https://orcid.org/0000-0001-8928-9821"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Srinivas Parthasarathy","raw_affiliation_strings":["University of Texas at Dallas, Work on this project performed as an intern at Microsoft Research Labs Redmond, WA, Dallas, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Dallas, Work on this project performed as an intern at Microsoft Research Labs Redmond, WA, Dallas, TX, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007425970","display_name":"Ivan Tashev","orcid":"https://orcid.org/0000-0002-2263-2047"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ivan Tashev","raw_affiliation_strings":["Microsoft Research Labs, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Labs, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.9414,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.93748695,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"121","last_page":"125"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9998000264167786,"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":0.9998000264167786,"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/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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9987999796867371,"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/computer-science","display_name":"Computer science","score":0.8107553720474243},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7103797197341919},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6993492841720581},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.5975560545921326},{"id":"https://openalex.org/keywords/sadness","display_name":"Sadness","score":0.5906583666801453},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5656746029853821},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5546457171440125},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.49554479122161865},{"id":"https://openalex.org/keywords/emotion-classification","display_name":"Emotion classification","score":0.48690736293792725},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4053211510181427},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34625867009162903},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08890214562416077}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8107553720474243},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7103797197341919},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6993492841720581},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.5975560545921326},{"id":"https://openalex.org/C2779812673","wikidata":"https://www.wikidata.org/wiki/Q169251","display_name":"Sadness","level":3,"score":0.5906583666801453},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5656746029853821},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5546457171440125},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.49554479122161865},{"id":"https://openalex.org/C206310091","wikidata":"https://www.wikidata.org/wiki/Q750859","display_name":"Emotion classification","level":2,"score":0.48690736293792725},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4053211510181427},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34625867009162903},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08890214562416077},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C118552586","wikidata":"https://www.wikidata.org/wiki/Q7867","display_name":"Psychiatry","level":1,"score":0.0},{"id":"https://openalex.org/C2779302386","wikidata":"https://www.wikidata.org/wiki/Q79871","display_name":"Anger","level":2,"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/iwaenc.2018.8521333","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwaenc.2018.8521333","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 16th International Workshop on Acoustic Signal Enhancement (IWAENC)","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":25,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1987048275","https://openalex.org/W2109255472","https://openalex.org/W2134557905","https://openalex.org/W2136922672","https://openalex.org/W2153897396","https://openalex.org/W2154780170","https://openalex.org/W2179352600","https://openalex.org/W2295001676","https://openalex.org/W2408520939","https://openalex.org/W2552810951","https://openalex.org/W2576530755","https://openalex.org/W2578895956","https://openalex.org/W2598207902","https://openalex.org/W2599621350","https://openalex.org/W2740546776","https://openalex.org/W2765860599","https://openalex.org/W2786657259","https://openalex.org/W2963467407","https://openalex.org/W2964121744","https://openalex.org/W6631190155","https://openalex.org/W6676338569","https://openalex.org/W6697498398","https://openalex.org/W6714031499","https://openalex.org/W6741935458"],"related_works":["https://openalex.org/W4401096132","https://openalex.org/W4388134110","https://openalex.org/W2400641934","https://openalex.org/W2018346846","https://openalex.org/W2028755160","https://openalex.org/W2041541161","https://openalex.org/W3206592872","https://openalex.org/W4210397330","https://openalex.org/W3167551411","https://openalex.org/W2143086761"],"abstract_inverted_index":{"Affect":[0],"recognition":[1,30],"plays":[2],"an":[3,22],"important":[4,23],"role":[5],"in":[6],"human":[7],"computer":[8],"interaction":[9],"(HCI).":[10],"Speech":[11],"is":[12,21],"one":[13],"of":[14,18,136,154,158,166],"the":[15,33,56,66,75,92,146,162],"primary":[16],"forms":[17],"expression":[19],"and":[20,61,79],"modality":[24],"for":[25,59,91,116,145],"emotion":[26,67,93,118],"recognition.":[27,119],"While":[28],"multiple":[29],"systems":[31],"exist,":[32],"most":[34],"common":[35],"ones":[36],"identify":[37],"discrete":[38],"categories":[39],"such":[40],"as":[41],"happiness,":[42],"sadness,":[43],"from":[44,104],"distinct":[45],"utterances":[46],"that":[47],"are":[48,63],"a":[49,141,152],"few":[50],"seconds":[51],"long.":[52],"In":[53,96,108],"many":[54],"cases":[55],"datasets,":[57],"used":[58],"training":[60],"evaluation,":[62],"imbalanced":[64],"across":[65],"labels.":[68],"This":[69],"leads":[70],"to":[71,139,161],"big":[72],"discrepancies":[73],"between":[74],"unweighted":[76],"accuracy":[77,81],"(UA)":[78],"weighted":[80],"(WA).":[82],"Recently":[83],"Deep":[84],"Neural":[85,99],"Networks":[86,100],"have":[87],"shown":[88],"increased":[89],"performance":[90,122,153,165],"classification":[94],"task.":[95],"particular":[97],"Convolutional":[98],"capture":[101],"contextual":[102],"information":[103],"speech":[105,117],"feature":[106],"frames.":[107],"this":[109],"paper":[110],"we":[111,129],"analyze":[112,130],"various":[113,131],"convolutional":[114,137],"architectures":[115],"We":[120],"report":[121],"on":[123,134],"different":[124],"frame":[125],"level":[126,143],"features.":[127],"Further":[128],"pooling":[132],"techniques,":[133],"top":[135],"layers,":[138],"get":[140],"utterance":[142],"representation":[144],"emotion.":[147],"Our":[148],"best":[149],"system":[150],"provides":[151],"UA":[155],"+":[156],"WA":[157],"121.15":[159],"compared":[160],"baseline":[163],"algorithm":[164],"118.10.":[167]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":7}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}