{"id":"https://openalex.org/W3007558004","doi":"https://doi.org/10.1109/asru46091.2019.9004037","title":"Spatio-Temporal Context Modelling for Speech Emotion Classification","display_name":"Spatio-Temporal Context Modelling for Speech Emotion Classification","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3007558004","doi":"https://doi.org/10.1109/asru46091.2019.9004037","mag":"3007558004"},"language":"en","primary_location":{"id":"doi:10.1109/asru46091.2019.9004037","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9004037","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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 Research Group (SPandH), The University of Sheffield, Sheffield, UK"],"affiliations":[{"raw_affiliation_string":"Speech and Hearing Research Group (SPandH), The University of Sheffield, Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033198799","display_name":"Roger K. Moore","orcid":"https://orcid.org/0000-0003-0065-3311"},"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":"Roger K Moore","raw_affiliation_strings":["Speech and Hearing Research Group (SPandH), The University of Sheffield, Sheffield, UK"],"affiliations":[{"raw_affiliation_string":"Speech and Hearing Research Group (SPandH), The University of Sheffield, Sheffield, UK","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 Research Group (SPandH), The University of Sheffield, Sheffield, UK"],"affiliations":[{"raw_affiliation_string":"Speech and Hearing Research Group (SPandH), The University of Sheffield, Sheffield, UK","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":1.7272,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.85538536,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"853","last_page":"859"},"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":0.9926000237464905,"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":0.9915000200271606,"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":0.7721849083900452},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5660703182220459},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5631586313247681},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5226090550422668},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4614514112472534},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4576167166233063},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.43855082988739014},{"id":"https://openalex.org/keywords/emotion-classification","display_name":"Emotion classification","score":0.4315446615219116},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4188382923603058},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38575130701065063}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7721849083900452},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5660703182220459},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5631586313247681},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5226090550422668},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4614514112472534},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4576167166233063},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.43855082988739014},{"id":"https://openalex.org/C206310091","wikidata":"https://www.wikidata.org/wiki/Q750859","display_name":"Emotion classification","level":2,"score":0.4315446615219116},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4188382923603058},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38575130701065063},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/asru46091.2019.9004037","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9004037","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W28412257","https://openalex.org/W605575788","https://openalex.org/W1501669607","https://openalex.org/W1522301498","https://openalex.org/W1611910665","https://openalex.org/W1836465849","https://openalex.org/W1928278792","https://openalex.org/W1974470404","https://openalex.org/W2055911634","https://openalex.org/W2085662862","https://openalex.org/W2095176743","https://openalex.org/W2110052520","https://openalex.org/W2125610823","https://openalex.org/W2146334809","https://openalex.org/W2239141610","https://openalex.org/W2296643551","https://openalex.org/W2409534643","https://openalex.org/W2578895956","https://openalex.org/W2625297138","https://openalex.org/W2747664154","https://openalex.org/W2765998482","https://openalex.org/W2766196653","https://openalex.org/W2788658682","https://openalex.org/W2803193013","https://openalex.org/W2804078698","https://openalex.org/W2889374687","https://openalex.org/W2899366898","https://openalex.org/W2899771611","https://openalex.org/W2919115771","https://openalex.org/W2936113082","https://openalex.org/W2949117887","https://openalex.org/W2963091558","https://openalex.org/W2963716183","https://openalex.org/W2963911037","https://openalex.org/W2964121744","https://openalex.org/W2972811324","https://openalex.org/W4239447739","https://openalex.org/W4293506044","https://openalex.org/W6631190155","https://openalex.org/W6636373857","https://openalex.org/W6638444622","https://openalex.org/W6638667902","https://openalex.org/W6676494506","https://openalex.org/W6748869263","https://openalex.org/W6756040250","https://openalex.org/W6766511095"],"related_works":["https://openalex.org/W2905271011","https://openalex.org/W3164948662","https://openalex.org/W4289536128","https://openalex.org/W3153597579","https://openalex.org/W1550318927","https://openalex.org/W4305042383","https://openalex.org/W2546649374","https://openalex.org/W2773396412","https://openalex.org/W4380854332","https://openalex.org/W2184859701"],"abstract_inverted_index":{"Speech":[0,139],"emotion":[1,32,140,170],"recognition":[2],"(SER)":[3],"is":[4,22,63,77,141,152],"a":[5,27,68,96,128,142,155],"requisite":[6],"for":[7,30,74,122,131,136,166],"emotional":[8,54],"intelligence":[9],"that":[10],"affects":[11],"the":[12,18,31,36,43,133,161],"understanding":[13],"of":[14,17,59,158],"speech.":[15],"One":[16],"most":[19],"crucial":[20],"tasks":[21,172],"to":[23,42,79],"obtain":[24],"patterns":[25,135],"having":[26],"maximum":[28],"correlation":[29],"classification":[33,171],"task":[34],"from":[35],"speech":[37,137],"signal":[38],"while":[39],"being":[40],"invariant":[41],"changes":[44],"in":[45],"frequency,":[46],"time":[47],"and":[48,61,102,118,163,168,173],"other":[49],"external":[50],"distortions.":[51],"Therefore,":[52],"learning":[53],"contextual":[55],"feature":[56,81,91],"representation":[57,82],"independent":[58],"speaker":[60],"environment":[62],"essential.":[64],"In":[65],"this":[66],"paper,":[67],"novel":[69],"spatiotemporal":[70,108],"context":[71,86,123],"modelling":[72],"framework":[73,94],"robust":[75],"SER":[76],"proposed":[78,150],"learn":[80],"by":[83],"using":[84],"acoustic":[85],"expansion":[87],"with":[88,154],"high":[89,114],"dimensional":[90,115],"projection.":[92],"The":[93,105,110,149],"uses":[95],"deep":[97],"convolutional":[98],"neural":[99],"network":[100,112],"(CNN)":[101],"self-attention":[103],"network.":[104],"CNNs":[106],"combine":[107],"features.":[109],"attention":[111],"produces":[113],"task-specific":[116],"features":[117,121],"combines":[119],"these":[120],"modelling,":[124],"which":[125],"altogether":[126],"provides":[127],"state-of-the-art":[129,177],"technique":[130],"classifying":[132],"extracted":[134],"emotion.":[138],"categorical":[143],"perception":[144],"representing":[145],"discrete":[146],"sensory":[147],"events.":[148],"approach":[151],"compared":[153],"wide":[156],"range":[157],"architectures":[159],"on":[160],"RAVDESS":[162],"IEMOCAP":[164],"corpora":[165],"8-class":[167],"4-class":[169],"remarkable":[174],"gain":[175],"over":[176],"systems":[178],"are":[179],"obtained,":[180],"absolutely":[181],"15%,":[182],"10%":[183],"respectively.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}