{"id":"https://openalex.org/W3096136448","doi":"https://doi.org/10.21437/interspeech.2020-3007","title":"Empirical Interpretation of Speech Emotion Perception with Attention Based Model for Speech Emotion Recognition","display_name":"Empirical Interpretation of Speech Emotion Perception with Attention Based Model for Speech Emotion Recognition","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3096136448","doi":"https://doi.org/10.21437/interspeech.2020-3007","mag":"3096136448"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-3007","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-3007","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","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/A5113981675","display_name":"Md Asif Jalal","orcid":null},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Md. Asif Jalal","raw_affiliation_strings":["Speech and Hearing Group (SPandH), The University of Sheffield"],"affiliations":[{"raw_affiliation_string":"Speech and Hearing Group (SPandH), The University of Sheffield","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078789113","display_name":"Rosanna Milner","orcid":"https://orcid.org/0000-0001-8924-0593"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Rosanna Milner","raw_affiliation_strings":["Speech and Hearing Group (SPandH), The University of Sheffield"],"affiliations":[{"raw_affiliation_string":"Speech and Hearing Group (SPandH), The University of Sheffield","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030528300","display_name":"Thomas Hain","orcid":"https://orcid.org/0000-0003-0939-3464"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Thomas Hain","raw_affiliation_strings":["Speech and Hearing Group (SPandH), The University of Sheffield"],"affiliations":[{"raw_affiliation_string":"Speech and Hearing Group (SPandH), The University of Sheffield","institution_ids":["https://openalex.org/I91136226"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5113981675"],"corresponding_institution_ids":["https://openalex.org/I91136226"],"apc_list":null,"apc_paid":null,"fwci":4.2707,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.94703723,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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/T10860","display_name":"Speech and Audio Processing","score":0.9984999895095825,"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/T11448","display_name":"Face recognition and analysis","score":0.9950000047683716,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/emotion-recognition","display_name":"Emotion recognition","score":0.7216742038726807},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6994338631629944},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.6389576196670532},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5792058706283569},{"id":"https://openalex.org/keywords/interpretation","display_name":"Interpretation (philosophy)","score":0.551257848739624},{"id":"https://openalex.org/keywords/speech-perception","display_name":"Speech perception","score":0.4831823408603668},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.4021075665950775},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.33253854513168335}],"concepts":[{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.7216742038726807},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6994338631629944},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6389576196670532},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5792058706283569},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.551257848739624},{"id":"https://openalex.org/C99209842","wikidata":"https://www.wikidata.org/wiki/Q643696","display_name":"Speech perception","level":3,"score":0.4831823408603668},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.4021075665950775},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.33253854513168335},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2020-3007","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-3007","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.whiterose.ac.uk:185082","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306400854","display_name":"White Rose Research Online (University of Leeds, The University of Sheffield, University of York)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2800616092","host_organization_name":"White Rose University Consortium","host_organization_lineage":["https://openalex.org/I2800616092"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Proceedings Paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W258847520","https://openalex.org/W1509274023","https://openalex.org/W1522301498","https://openalex.org/W1923034539","https://openalex.org/W1973900406","https://openalex.org/W1974470404","https://openalex.org/W1984327771","https://openalex.org/W2005708641","https://openalex.org/W2005854605","https://openalex.org/W2026984028","https://openalex.org/W2032211917","https://openalex.org/W2049333779","https://openalex.org/W2055911634","https://openalex.org/W2061068689","https://openalex.org/W2074788634","https://openalex.org/W2080576537","https://openalex.org/W2089679554","https://openalex.org/W2110052520","https://openalex.org/W2111056602","https://openalex.org/W2111926505","https://openalex.org/W2131774270","https://openalex.org/W2137639365","https://openalex.org/W2146334809","https://openalex.org/W2239141610","https://openalex.org/W2321825897","https://openalex.org/W2339343773","https://openalex.org/W2409534643","https://openalex.org/W2625297138","https://openalex.org/W2747664154","https://openalex.org/W2765998482","https://openalex.org/W2888869035","https://openalex.org/W2889374687","https://openalex.org/W2899366898","https://openalex.org/W2899771611","https://openalex.org/W2936113082","https://openalex.org/W2964121744","https://openalex.org/W2972811324","https://openalex.org/W2972965453","https://openalex.org/W3007558004","https://openalex.org/W3008554267","https://openalex.org/W3094412822","https://openalex.org/W4239447739","https://openalex.org/W4245733664","https://openalex.org/W4251326366","https://openalex.org/W4300985914"],"related_works":["https://openalex.org/W3183204001","https://openalex.org/W4327743144","https://openalex.org/W4386782890","https://openalex.org/W4313320911","https://openalex.org/W1997436241","https://openalex.org/W2367733278","https://openalex.org/W3126677997","https://openalex.org/W1014786583","https://openalex.org/W3152454717","https://openalex.org/W1984044622"],"abstract_inverted_index":{"Speech":[0],"emotion":[1,61,79,104,123,177],"recognition":[2,80],"is":[3,116,128,138,145,166],"essential":[4],"for":[5,118,175],"obtaining":[6],"emotional":[7,46],"intelligence":[8],"which":[9,144],"affects":[10],"the":[11,45,119,131,161,169,181,184],"understanding":[12],"of":[13,17,54,102,110,121],"context":[14,47,112],"and":[15,22,27,51,88,113,134,156,164,183],"meaning":[16],"speech.":[18],"Harmonically":[19],"structured":[20],"vowel":[21,37,170],"consonant":[23],"sounds":[24,171],"add":[25],"indexical":[26],"linguistic":[28,52],"cues":[29,39,179],"in":[30,43,65,76],"spoken":[31],"information.":[32],"Previous":[33],"research":[34,57],"argued":[35],"whether":[36],"sound":[38],"were":[40],"more":[41,173],"important":[42,174],"carrying":[44],"from":[48],"a":[49,85,89],"psychological":[50],"point":[53],"view.":[55],"Other":[56],"also":[58],"claimed":[59],"that":[60,168],"information":[62],"could":[63],"exist":[64],"small":[66],"overlapping":[67],"acoustic":[68,111,142,178,192],"cues.":[69],"However,":[70],"these":[71,100],"claims":[72],"are":[73,96,158,172],"not":[74],"corroborated":[75],"computational":[77,106],"speech":[78,103,122],"systems.":[81],"In":[82],"this":[83,152],"research,":[84],"convolution-based":[86],"model":[87,185],"long-short-term":[90],"memory-based":[91],"model,":[92],"both":[93],"using":[94],"attention,":[95],"applied":[97],"to":[98,160],"investigate":[99],"theories":[101],"on":[105,140,151,191],"models.":[107],"The":[108,125,154],"role":[109],"word":[114,188],"importance":[115,189],"demonstrated":[117],"task":[120],"recognition.":[124],"IEMOCAP":[126],"corpus":[127],"evaluated":[129],"by":[130],"proposed":[132],"models,":[133],"80.1%":[135],"unweighted":[136],"accuracy":[137],"achieved":[139],"pure":[141],"data":[143],"higher":[146],"than":[147,180],"current":[148],"state-of-the-art":[149],"models":[150],"task.":[153],"phones":[155],"words":[157],"mapped":[159],"attention":[162],"vectors":[163],"it":[165],"seen":[167],"defining":[176],"consonants,":[182],"can":[186],"assign":[187],"based":[190],"context.":[193]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}