{"id":"https://openalex.org/W2889286050","doi":"https://doi.org/10.21437/interspeech.2018-1858","title":"Towards Temporal Modelling of Categorical Speech Emotion Recognition","display_name":"Towards Temporal Modelling of Categorical Speech Emotion Recognition","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2889286050","doi":"https://doi.org/10.21437/interspeech.2018-1858","mag":"2889286050"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-1858","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1858","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","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/A5100538929","display_name":"Wenjing Han","orcid":null},"institutions":[{"id":"https://openalex.org/I4210155230","display_name":"Samsung (China)","ror":"https://ror.org/04yt00889","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210155230"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wenjing Han","raw_affiliation_strings":["Samsung Research Institute China Beijing (SRC-B), Beijing, China"],"affiliations":[{"raw_affiliation_string":"Samsung Research Institute China Beijing (SRC-B), Beijing, China","institution_ids":["https://openalex.org/I4210155230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058607469","display_name":"Huabin Ruan","orcid":"https://orcid.org/0000-0002-0507-5568"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huabin Ruan","raw_affiliation_strings":["Protein Research Technology Center, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Protein Research Technology Center, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100373745","display_name":"Xiaohong Chen","orcid":"https://orcid.org/0000-0002-9797-8384"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaomin Chen","raw_affiliation_strings":["School of Computing Science and Technology, Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"School of Computing Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100700404","display_name":"Zhixiang Wang","orcid":"https://orcid.org/0000-0002-5016-587X"},"institutions":[{"id":"https://openalex.org/I4210155230","display_name":"Samsung (China)","ror":"https://ror.org/04yt00889","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210155230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhixiang Wang","raw_affiliation_strings":["Samsung Research Institute China Beijing (SRC-B), Beijing, China"],"affiliations":[{"raw_affiliation_string":"Samsung Research Institute China Beijing (SRC-B), Beijing, China","institution_ids":["https://openalex.org/I4210155230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100398343","display_name":"Haifeng Li","orcid":"https://orcid.org/0000-0002-2534-2299"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haifeng Li","raw_affiliation_strings":["School of Computing Science and Technology, Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"School of Computing Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043060302","display_name":"Bj\u00f6rn W. Schuller","orcid":"https://orcid.org/0000-0002-6478-8699"},"institutions":[{"id":"https://openalex.org/I179225836","display_name":"University of Augsburg","ror":"https://ror.org/03p14d497","country_code":"DE","type":"education","lineage":["https://openalex.org/I179225836"]},{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN","DE"],"is_corresponding":false,"raw_author_name":"Bj\u00f6rn Schuller","raw_affiliation_strings":["GLAM -Group on Language, Audio & Music, Imperial College London, U.K","School of Computing Science and Technology, Harbin Institute of Technology, Harbin, China","ZD.B Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Germany"],"affiliations":[{"raw_affiliation_string":"GLAM -Group on Language, Audio & Music, Imperial College London, U.K","institution_ids":[]},{"raw_affiliation_string":"School of Computing Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"ZD.B Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Germany","institution_ids":["https://openalex.org/I179225836"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100538929"],"corresponding_institution_ids":["https://openalex.org/I4210155230"],"apc_list":null,"apc_paid":null,"fwci":5.9229,"has_fulltext":false,"cited_by_count":53,"citation_normalized_percentile":{"value":0.9691188,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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"}},{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9994999766349792,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7122706770896912},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.6639745235443115},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6369368433952332},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.6158299446105957},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45190468430519104},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3832210600376129},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.13985416293144226}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7122706770896912},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.6639745235443115},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6369368433952332},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.6158299446105957},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45190468430519104},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3832210600376129},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.13985416293144226}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2018-1858","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1858","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},{"id":"pmh:oai:uni-augsburg.opus-bayern.de:71817","is_oa":false,"landing_page_url":"https://opus.bibliothek.uni-augsburg.de/opus4/frontdoor/index/index/docId/71817","pdf_url":null,"source":{"id":"https://openalex.org/S4306400930","display_name":"OPUS (Augsburg University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119916105","host_organization_name":"Augsburg University","host_organization_lineage":["https://openalex.org/I119916105"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"bookpart"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W183625566","https://openalex.org/W211912913","https://openalex.org/W1902237438","https://openalex.org/W2000982178","https://openalex.org/W2016661008","https://openalex.org/W2074788634","https://openalex.org/W2090777335","https://openalex.org/W2110052520","https://openalex.org/W2110709236","https://openalex.org/W2111072639","https://openalex.org/W2125838338","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2143492886","https://openalex.org/W2146334809","https://openalex.org/W2152563462","https://openalex.org/W2193413348","https://openalex.org/W2239141610","https://openalex.org/W2327797865","https://openalex.org/W2357061213","https://openalex.org/W2395587375","https://openalex.org/W2399733683","https://openalex.org/W2408520939","https://openalex.org/W2512885694","https://openalex.org/W2513507089","https://openalex.org/W2518511005","https://openalex.org/W2583743457","https://openalex.org/W2625297138","https://openalex.org/W2648194195","https://openalex.org/W2750666523","https://openalex.org/W2786779322","https://openalex.org/W2962736520","https://openalex.org/W2964308564","https://openalex.org/W4239447739","https://openalex.org/W4253573210"],"related_works":["https://openalex.org/W4386799044","https://openalex.org/W2773208253","https://openalex.org/W2560646951","https://openalex.org/W4297454206","https://openalex.org/W65104662","https://openalex.org/W1871748041","https://openalex.org/W2362286668","https://openalex.org/W2133382151","https://openalex.org/W2153339597","https://openalex.org/W3126677997"],"abstract_inverted_index":{"To":[0],"model":[1,101],"the":[2,12,20,78,82,88,121,130,138],"categorical":[3,21],"speech":[4],"emotion":[5],"recognition":[6],"task":[7],"in":[8],"a":[9,27,34,73,93],"temporal":[10,99],"manner,":[11],"first":[13],"challenge":[14],"arising":[15],"is":[16,39],"how":[17],"to":[18,51,66,102,137],"transfer":[19],"label":[22,28,70,104],"for":[23],"each":[24],"utterance":[25,38],"into":[26],"sequence.To":[29],"settle":[30],"this,":[31],"we":[32,64,91],"make":[33],"hypothesis":[35,126],"that":[36],"an":[37,68,107],"consisting":[40],"of":[41,75,132],"emotional":[42,79,83,109,112],"and":[43,46,85,105,127],"non-emotional":[44,48,89,115],"segments,":[45],"these":[47],"segments":[49,110,116],"correspond":[50],"silent":[52],"regions,":[53],"short":[54],"pauses,":[55],"transitions":[56],"between":[57],"phonemes,":[58,60],"unvoiced":[59],"etc.With":[61],"this":[62],"hypothesis,":[63],"propose":[65],"treat":[67],"utterance's":[69,108],"sequence":[71],"as":[72],"chain":[74],"two":[76],"states:":[77],"state":[80],"denoting":[81,87],"frame":[84],"Null":[86],"frame.Then,":[90],"exploit":[92],"recurrent":[94],"neural":[95],"network":[96],"based":[97],"connectionist":[98],"classification":[100],"automatically":[103],"align":[106],"with":[111,117],"labels,":[113],"while":[114],"Nulls.Experimental":[118],"results":[119],"on":[120],"IEMOCAP":[122],"corpus":[123],"validate":[124],"our":[125,133],"also":[128],"demonstrate":[129],"effectiveness":[131],"proposed":[134],"method":[135],"compared":[136],"state-of-the-art":[139],"algorithms.":[140]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}