{"id":"https://openalex.org/W3162589478","doi":"https://doi.org/10.1109/icassp39728.2021.9414248","title":"Speech Emotion Recognition Using Quaternion Convolutional Neural Networks","display_name":"Speech Emotion Recognition Using Quaternion Convolutional Neural Networks","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3162589478","doi":"https://doi.org/10.1109/icassp39728.2021.9414248","mag":"3162589478"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414248","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414248","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5042996482","display_name":"Aneesh Muppidi","orcid":null},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aneesh Muppidi","raw_affiliation_strings":["Stony Brook University, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stony Brook University, NY, USA","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023415990","display_name":"Martin Radfar","orcid":null},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Martin Radfar","raw_affiliation_strings":["Stony Brook University, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stony Brook University, NY, USA","institution_ids":["https://openalex.org/I59553526"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I59553526"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":60,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6309","last_page":"6313"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9991999864578247,"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":0.9987000226974487,"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":0.7577698230743408},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.696247398853302},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6713731288909912},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6699340343475342},{"id":"https://openalex.org/keywords/quaternion","display_name":"Quaternion","score":0.6605385541915894},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4680255055427551},{"id":"https://openalex.org/keywords/motion-capture","display_name":"Motion capture","score":0.4648626744747162},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.45458826422691345},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.4299386143684387},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3699352741241455},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.2916453778743744},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08662360906600952}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7577698230743408},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.696247398853302},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6713731288909912},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6699340343475342},{"id":"https://openalex.org/C200127275","wikidata":"https://www.wikidata.org/wiki/Q173853","display_name":"Quaternion","level":2,"score":0.6605385541915894},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4680255055427551},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.4648626744747162},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.45458826422691345},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.4299386143684387},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3699352741241455},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.2916453778743744},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08662360906600952},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414248","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414248","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.6000000238418579,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W80623023","https://openalex.org/W175750906","https://openalex.org/W1533861849","https://openalex.org/W2005708641","https://openalex.org/W2137519524","https://openalex.org/W2146334809","https://openalex.org/W2161073241","https://openalex.org/W2162753443","https://openalex.org/W2168249605","https://openalex.org/W2168961642","https://openalex.org/W2578895956","https://openalex.org/W2585379661","https://openalex.org/W2747664154","https://openalex.org/W2777468850","https://openalex.org/W2787378487","https://openalex.org/W2803193013","https://openalex.org/W2894977338","https://openalex.org/W2963103134","https://openalex.org/W2963211739","https://openalex.org/W2963341071","https://openalex.org/W2963719423","https://openalex.org/W2964300796","https://openalex.org/W2972602947","https://openalex.org/W2972691009","https://openalex.org/W2985882473","https://openalex.org/W2995819149","https://openalex.org/W2997700007","https://openalex.org/W3008039831","https://openalex.org/W3012473796","https://openalex.org/W3023420897","https://openalex.org/W3205498744","https://openalex.org/W6603295077","https://openalex.org/W6607193717","https://openalex.org/W6631943919","https://openalex.org/W6735429107","https://openalex.org/W6774704184"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W4402568167","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W1923358586","https://openalex.org/W2184242386","https://openalex.org/W2325729322"],"abstract_inverted_index":{"Although":[0],"speech":[1,11,30,40],"recognition":[2,32],"has":[3],"become":[4],"a":[5,14,23],"widespread":[6],"technology,":[7],"inferring":[8],"emotion":[9,31],"from":[10],"signals":[12,41],"remains":[13],"challenge.":[15],"Our":[16],"paper":[17],"addresses":[18],"this":[19],"problem":[20],"by":[21],"proposing":[22],"quaternion":[24,47,133],"convolutional":[25],"neural":[26],"network":[27],"(QCNN)":[28],"based":[29,54],"(SER)":[33],"model":[34,56,85,109,127],"in":[35,44,61,93],"which":[36],"Mel-spectrogram":[37],"features":[38],"of":[39,66,78,113],"are":[42],"encoded":[43],"an":[45,111],"RGB":[46],"domain.":[48],"We":[49],"demonstrate":[50],"that":[51,131],"our":[52,79],"QCNN":[53,84],"SER":[55],"outperforms":[57],"other":[58],"real-valued":[59,145],"methods":[60,92],"the":[62,76,94,108,119,132],"Ryerson":[63],"Audio-Visual":[64],"Database":[65],"Emotional":[67,96],"Speech":[68],"and":[69,102,116,122],"Song":[70],"(RAVDESS,":[71],"8-classes)":[72],"dataset,":[73],"achieving,":[74],"to":[75,140],"best":[77],"knowledge,":[80],"state-of-the-art":[81,91],"results.":[82],"The":[83],"also":[86],"achieves":[87,110],"comparable":[88],"results":[89,129],"with":[90],"Interactive":[95],"Dyadic":[97],"Motion":[98],"Capture":[99],"(IEMOCAP":[100],"4-classes)":[101],"Berlin":[103],"EMO-DB":[104,123],"(7-classes)":[105],"datasets.":[106],"Specifically,":[107],"accuracy":[112],"77.87%,":[114],"70.46%,":[115],"88.78%":[117],"for":[118],"RAVDESS,":[120],"IEMOCAP,":[121],"datasets,":[124],"respectively.":[125],"Additionally,":[126],"size":[128],"reveal":[130],"unit":[134],"structure":[135],"is":[136],"significantly":[137],"better":[138],"able":[139],"encode":[141],"internal":[142],"dependencies":[143],"than":[144],"structures.":[146]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":19},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}