{"id":"https://openalex.org/W3015240477","doi":"https://doi.org/10.1109/icassp40776.2020.9054073","title":"Multi-Head Attention for Speech Emotion Recognition with Auxiliary Learning of Gender Recognition","display_name":"Multi-Head Attention for Speech Emotion Recognition with Auxiliary Learning of Gender Recognition","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015240477","doi":"https://doi.org/10.1109/icassp40776.2020.9054073","mag":"3015240477"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054073","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054073","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5051372626","display_name":"Anish Nediyanchath","orcid":null},"institutions":[{"id":"https://openalex.org/I4210139030","display_name":"Samsung (India)","ror":"https://ror.org/04cpx2569","country_code":"IN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210139030"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Anish Nediyanchath","raw_affiliation_strings":["Samsung R&D Institute India \u2013 Bangalore"],"affiliations":[{"raw_affiliation_string":"Samsung R&D Institute India \u2013 Bangalore","institution_ids":["https://openalex.org/I4210139030"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073202047","display_name":"Periyasamy Paramasivam","orcid":null},"institutions":[{"id":"https://openalex.org/I4210139030","display_name":"Samsung (India)","ror":"https://ror.org/04cpx2569","country_code":"IN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210139030"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Periyasamy Paramasivam","raw_affiliation_strings":["Samsung R&D Institute India \u2013 Bangalore"],"affiliations":[{"raw_affiliation_string":"Samsung R&D Institute India \u2013 Bangalore","institution_ids":["https://openalex.org/I4210139030"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014940317","display_name":"Promod Yenigalla","orcid":null},"institutions":[{"id":"https://openalex.org/I4210139030","display_name":"Samsung (India)","ror":"https://ror.org/04cpx2569","country_code":"IN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210139030"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Promod Yenigalla","raw_affiliation_strings":["Samsung R&D Institute India \u2013 Bangalore"],"affiliations":[{"raw_affiliation_string":"Samsung R&D Institute India \u2013 Bangalore","institution_ids":["https://openalex.org/I4210139030"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5051372626"],"corresponding_institution_ids":["https://openalex.org/I4210139030"],"apc_list":null,"apc_paid":null,"fwci":11.012,"has_fulltext":false,"cited_by_count":88,"citation_normalized_percentile":{"value":0.98757106,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"7179","last_page":"7183"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9975000023841858,"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":0.7424043416976929},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7204743027687073},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6682984828948975},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6473087072372437},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.5987221598625183},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5297437906265259},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5044299364089966},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4993476867675781},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4499198794364929},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.41500282287597656},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3411022424697876},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3401355743408203},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.12094005942344666},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07405295968055725}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7424043416976929},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7204743027687073},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6682984828948975},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6473087072372437},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5987221598625183},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5297437906265259},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5044299364089966},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4993476867675781},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4499198794364929},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.41500282287597656},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3411022424697876},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3401355743408203},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.12094005942344666},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07405295968055725},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054073","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054073","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7099999785423279,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1994885532","https://openalex.org/W2016661008","https://openalex.org/W2054857826","https://openalex.org/W2074788634","https://openalex.org/W2088506445","https://openalex.org/W2099767163","https://openalex.org/W2146334809","https://openalex.org/W2163685610","https://openalex.org/W2295001676","https://openalex.org/W2408520939","https://openalex.org/W2747664154","https://openalex.org/W2757445263","https://openalex.org/W2787322890","https://openalex.org/W2804753883","https://openalex.org/W2806051338","https://openalex.org/W2809734421","https://openalex.org/W2886300652","https://openalex.org/W2889169802","https://openalex.org/W2889191349","https://openalex.org/W2896457183","https://openalex.org/W2912728762","https://openalex.org/W2962736520","https://openalex.org/W2962770129","https://openalex.org/W2962778134","https://openalex.org/W2962824709","https://openalex.org/W2963403868","https://openalex.org/W2963467407","https://openalex.org/W2963800675","https://openalex.org/W2964171275","https://openalex.org/W3013686035","https://openalex.org/W4385245566","https://openalex.org/W6697498398","https://openalex.org/W6714031499","https://openalex.org/W6738763440","https://openalex.org/W6739901393","https://openalex.org/W6751883949","https://openalex.org/W6755207826","https://openalex.org/W6755596326","https://openalex.org/W6775162343","https://openalex.org/W7048126131"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W3111219495","https://openalex.org/W4375867731","https://openalex.org/W2183306018","https://openalex.org/W2549990292","https://openalex.org/W2345479200","https://openalex.org/W3097502728","https://openalex.org/W2951819827","https://openalex.org/W2849310602","https://openalex.org/W2611989081"],"abstract_inverted_index":{"The":[0,25,46,85],"paper":[1],"presents":[2],"a":[3],"Multi-Head":[4,69],"Attention":[5,70],"deep":[6],"learning":[7,77,90],"network":[8],"for":[9,152],"Speech":[10,108],"Emotion":[11,109],"Recognition":[12],"(SER)":[13],"using":[14],"Log":[15],"mel-Filter":[16],"Bank":[17],"Energies":[18],"(LFBE)":[19],"spectral":[20],"features":[21,56,62,94],"as":[22,81],"the":[23,30,41,53,61,64,91,97,111,146],"input.":[24],"multi-head":[26],"attention":[27],"along":[28],"with":[29,78],"position":[31,47,72],"embedding":[32,48],"jointly":[33],"attends":[34],"to":[35,52,68,125],"information":[36],"from":[37],"different":[38],"representations":[39],"of":[40,60,107,130,136],"same":[42],"LFBE":[43],"input":[44],"sequence.":[45,65],"helps":[49,88],"in":[50,63,89,100,104],"attending":[51],"dominant":[54],"emotion":[55,98,154],"by":[57],"identifying":[58],"positions":[59],"In":[66],"addition":[67],"and":[71,102,132,141],"embedding,":[73],"we":[74],"apply":[75],"multi-task":[76],"gender":[79,92],"recognition":[80],"an":[82,127],"auxiliary":[83,86],"task.":[84,113],"task":[87],"specific":[93],"that":[95],"influence":[96],"characteristics":[99],"speech":[101],"results":[103],"improved":[105],"accuracy":[106,129,135],"Recognition,":[110],"primary":[112],"We":[114,122],"conducted":[115],"all":[116],"our":[117],"experiments":[118],"on":[119,150],"IEMOCAP":[120],"dataset.":[121],"are":[123,139],"able":[124],"achieve":[126],"overall":[128],"76.4%":[131],"average":[133],"class":[134],"70.1%,":[137],"which":[138],"5.3%":[140],"6.2%":[142],"higher":[143],"respectively":[144],"than":[145],"state-of-the-art":[147],"models":[148],"available":[149],"SER":[151],"four":[153],"classes.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":30},{"year":2022,"cited_by_count":16},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-05T09:29:38.588285","created_date":"2025-10-10T00:00:00"}