{"id":"https://openalex.org/W2972811324","doi":"https://doi.org/10.21437/interspeech.2019-3068","title":"Learning Temporal Clusters Using Capsule Routing for Speech Emotion Recognition","display_name":"Learning Temporal Clusters Using Capsule Routing for Speech Emotion Recognition","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2972811324","doi":"https://doi.org/10.21437/interspeech.2019-3068","mag":"2972811324"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-3068","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-3068","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","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":false,"raw_author_name":"Md. Asif Jalal","raw_affiliation_strings":["Speech and Hearing Research Group (SPandH), University of Sheffield, Sheffield, UK"],"affiliations":[{"raw_affiliation_string":"Speech and Hearing Research Group (SPandH), University of Sheffield, Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042184515","display_name":"Erfan Loweimi","orcid":"https://orcid.org/0000-0002-8761-021X"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Erfan Loweimi","raw_affiliation_strings":["Centre for Speech Technology Research (CSTR), University of Edinburgh, Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research (CSTR), University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"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), University of Sheffield, Sheffield, UK"],"affiliations":[{"raw_affiliation_string":"Speech and Hearing Research Group (SPandH), 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":true,"raw_author_name":"Thomas Hain","raw_affiliation_strings":["Speech and Hearing Research Group (SPandH), University of Sheffield, Sheffield, UK"],"affiliations":[{"raw_affiliation_string":"Speech and Hearing Research Group (SPandH), University of Sheffield, Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5030528300"],"corresponding_institution_ids":["https://openalex.org/I91136226"],"apc_list":null,"apc_paid":null,"fwci":7.8683,"has_fulltext":false,"cited_by_count":65,"citation_normalized_percentile":{"value":0.97831986,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"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":0.9997000098228455,"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/T11309","display_name":"Music and Audio Processing","score":0.9977999925613403,"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/T10860","display_name":"Speech and Audio Processing","score":0.9937000274658203,"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":0.7265604734420776},{"id":"https://openalex.org/keywords/routing","display_name":"Routing (electronic design automation)","score":0.5365282297134399},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5339955687522888},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.5221878886222839},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3280186355113983},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.16354387998580933}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7265604734420776},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.5365282297134399},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5339955687522888},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5221878886222839},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3280186355113983},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.16354387998580933}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2019-3068","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-3068","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.whiterose.ac.uk:167268","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"},{"id":"pmh:oai:repository@napier.ac.uk:3585898","is_oa":false,"landing_page_url":"http://researchrepository.napier.ac.uk/Output/3585898","pdf_url":null,"source":{"id":"https://openalex.org/S4306402591","display_name":"Edinburgh Napier Research Repository (Edinburgh Napier University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I251738","host_organization_name":"Edinburgh Napier University","host_organization_lineage":["https://openalex.org/I251738"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Presentation / Conference Contribution"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W605575788","https://openalex.org/W1501669607","https://openalex.org/W1522301498","https://openalex.org/W1531333757","https://openalex.org/W1536929369","https://openalex.org/W1562806204","https://openalex.org/W1666984270","https://openalex.org/W1974470404","https://openalex.org/W2041823554","https://openalex.org/W2055911634","https://openalex.org/W2069143585","https://openalex.org/W2087618018","https://openalex.org/W2110052520","https://openalex.org/W2131774270","https://openalex.org/W2150769028","https://openalex.org/W2151008812","https://openalex.org/W2239141610","https://openalex.org/W2296643551","https://openalex.org/W2399733683","https://openalex.org/W2402268235","https://openalex.org/W2408520939","https://openalex.org/W2409534643","https://openalex.org/W2578895956","https://openalex.org/W2625297138","https://openalex.org/W2765998482","https://openalex.org/W2785044468","https://openalex.org/W2803193013","https://openalex.org/W2899366898","https://openalex.org/W2899771611","https://openalex.org/W2963703618","https://openalex.org/W2964121744","https://openalex.org/W4239447739","https://openalex.org/W4310348270"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W2130043461","https://openalex.org/W2530322880","https://openalex.org/W3126677997"],"abstract_inverted_index":{"Emotion":[0],"recognition":[1],"from":[2,25],"speech":[3,93],"plays":[4],"a":[5,64,119,133],"significant":[6],"role":[7],"in":[8,42],"adding":[9],"emotional":[10],"intelligence":[11],"to":[12,30,51],"machines":[13],"and":[14,81,141,144,154,157,166],"making":[15],"human-machine":[16],"interaction":[17],"more":[18],"natural.":[19],"One":[20],"of":[21,54,91,109,136],"the":[22,38,88,92,102,106,110,124,139,171,175],"key":[23],"challenges":[24],"machine":[26],"learning":[27],"standpoint":[28],"is":[29,164],"extract":[31],"patterns":[32],"which":[33,116,163],"bear":[34],"maximum":[35],"correlation":[36],"with":[37,87,105,132],"emotion":[39,71],"information":[40,55,100],"encoded":[41],"this":[43,60],"signal":[44,94],"while":[45,101],"being":[46],"as":[47,49],"insensitive":[48],"possible":[50],"other":[52],"types":[53],"carried":[56],"by":[57,95],"speech.":[58],"In":[59],"paper,":[61],"we":[62],"propose":[63],"novel":[65],"temporal":[66,89,114],"modelling":[67],"framework":[68],"for":[69,122,174],"robust":[70],"classification":[72],"using":[73],"bidirectional":[74],"long":[75],"short-term":[76],"memory":[77],"network":[78],"(BLSTM),":[79],"CNN":[80,103],"Capsule":[82,111],"networks.":[83],"The":[84,127],"BLSTM":[85],"deals":[86],"dynamics":[90],"effectively":[96],"representing":[97],"forward/backward":[98],"contextual":[99],"along":[104],"dynamic":[107],"routing":[108],"net":[112],"learn":[113],"clusters":[115],"altogether":[117],"provide":[118],"state-of-the-art":[120,148],"technique":[121],"classifying":[123],"extracted":[125],"patterns.":[126],"proposed":[128],"approach":[129],"was":[130,160],"compared":[131],"wide":[134],"range":[135],"architectures":[137],"on":[138],"FAU-Aibo":[140],"RAVDESS":[142,155],"corpora":[143],"remarkable":[145],"gain":[146],"over":[147],"systems":[149],"were":[150],"obtained.":[151],"For":[152],"FAO-Aibo":[153],"77.6%":[156],"56.2%":[158],"accuracy":[159],"achieved,":[161],"respectively,":[162],"3%":[165],"14%":[167],"(absolute)":[168],"higher":[169],"than":[170],"best-reported":[172],"result":[173],"respective":[176],"tasks.":[177]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}