{"id":"https://openalex.org/W2939570038","doi":"https://doi.org/10.1109/icassp.2019.8683240","title":"Hierarchical Two-level Modelling of Emotional States in Spoken Dialog Systems","display_name":"Hierarchical Two-level Modelling of Emotional States in Spoken Dialog Systems","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2939570038","doi":"https://doi.org/10.1109/icassp.2019.8683240","mag":"2939570038"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683240","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683240","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5013838199","display_name":"Oxana Verkholyak","orcid":"https://orcid.org/0000-0002-5583-0410"},"institutions":[{"id":"https://openalex.org/I4210103826","display_name":"St. Petersburg Institute for Informatics and Automation","ror":"https://ror.org/01ccb9w37","country_code":"RU","type":"facility","lineage":["https://openalex.org/I4210103826"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Oxana Verkholyak","raw_affiliation_strings":["St. Petersburg Institute for Informatics and Automation of Russian Academy of Sciences, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"St. Petersburg Institute for Informatics and Automation of Russian Academy of Sciences, Russia","institution_ids":["https://openalex.org/I4210103826"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002620233","display_name":"Dmitrii Fedotov","orcid":null},"institutions":[{"id":"https://openalex.org/I196349391","display_name":"Universit\u00e4t Ulm","ror":"https://ror.org/032000t02","country_code":"DE","type":"education","lineage":["https://openalex.org/I196349391"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dmitrii Fedotov","raw_affiliation_strings":["Institute of Communications Engineering, Ulm University, Ulm, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Communications Engineering, Ulm University, Ulm, Germany","institution_ids":["https://openalex.org/I196349391"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050585145","display_name":"Heysem Kaya","orcid":"https://orcid.org/0000-0001-7947-5508"},"institutions":[{"id":"https://openalex.org/I125454184","display_name":"Tekirda\u011f Nam\u0131k Kemal University","ror":"https://ror.org/01a0mk874","country_code":"TR","type":"education","lineage":["https://openalex.org/I125454184"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Heysem Kaya","raw_affiliation_strings":["Department of Computer Engineering, Nam\u0131k Kemal University, \u00c7orlu, Tekirda\u011f, Turkey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Nam\u0131k Kemal University, \u00c7orlu, Tekirda\u011f, Turkey","institution_ids":["https://openalex.org/I125454184"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100354569","display_name":"Yang Zhang","orcid":"https://orcid.org/0000-0001-6777-3487"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Zhang","raw_affiliation_strings":["Huawei Noah\u2019s Ark Lab, Huawei Technologies, Shenzhen, China","Huawei Noah's Ark Lab, Huawei Technologies, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah\u2019s Ark Lab, Huawei Technologies, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Huawei Noah's Ark Lab, Huawei Technologies, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032870944","display_name":"Alexey Karpov","orcid":"https://orcid.org/0000-0003-3424-652X"},"institutions":[{"id":"https://openalex.org/I4210103826","display_name":"St. Petersburg Institute for Informatics and Automation","ror":"https://ror.org/01ccb9w37","country_code":"RU","type":"facility","lineage":["https://openalex.org/I4210103826"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Alexey Karpov","raw_affiliation_strings":["St. Petersburg Institute for Informatics and Automation of Russian Academy of Sciences, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"St. Petersburg Institute for Informatics and Automation of Russian Academy of Sciences, Russia","institution_ids":["https://openalex.org/I4210103826"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2519,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.78762696,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"6700","last_page":"6704"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9976000189781189,"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/T12031","display_name":"Speech and dialogue systems","score":0.9973999857902527,"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/computer-science","display_name":"Computer science","score":0.7903450131416321},{"id":"https://openalex.org/keywords/dialog-box","display_name":"Dialog box","score":0.7340309023857117},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6501020193099976},{"id":"https://openalex.org/keywords/valence","display_name":"Valence (chemistry)","score":0.5662904977798462},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5601562857627869},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5543547868728638},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5379379987716675},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5328778624534607},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.5267668962478638},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4864799678325653},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.13355329632759094}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7903450131416321},{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.7340309023857117},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6501020193099976},{"id":"https://openalex.org/C168900304","wikidata":"https://www.wikidata.org/wiki/Q171407","display_name":"Valence (chemistry)","level":2,"score":0.5662904977798462},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5601562857627869},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5543547868728638},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5379379987716675},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5328778624534607},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.5267668962478638},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4864799678325653},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.13355329632759094},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","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},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8683240","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683240","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 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":0.5899999737739563,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1608705073","https://openalex.org/W2055332436","https://openalex.org/W2090777335","https://openalex.org/W2091746061","https://openalex.org/W2136879928","https://openalex.org/W2146334809","https://openalex.org/W2148146486","https://openalex.org/W2161372178","https://openalex.org/W2243753858","https://openalex.org/W2399733683","https://openalex.org/W2407346284","https://openalex.org/W2511508976","https://openalex.org/W2513507089","https://openalex.org/W2578895956","https://openalex.org/W2759261664","https://openalex.org/W2805667789","https://openalex.org/W2889070090","https://openalex.org/W4243716403","https://openalex.org/W6680408311","https://openalex.org/W6681923411","https://openalex.org/W6690653271","https://openalex.org/W6752038596"],"related_works":["https://openalex.org/W2098987383","https://openalex.org/W2417260800","https://openalex.org/W1596203174","https://openalex.org/W2117933979","https://openalex.org/W4298396513","https://openalex.org/W2283130723","https://openalex.org/W103938586","https://openalex.org/W2104718772","https://openalex.org/W4233992201","https://openalex.org/W2086773623"],"abstract_inverted_index":{"Emotions":[0],"occur":[1],"in":[2,88],"complex":[3],"social":[4],"interactions,":[5],"and":[6,36,66,84,104],"thus":[7],"processing":[8],"of":[9,20,34,91,102],"isolated":[10],"utterances":[11],"may":[12],"not":[13],"be":[14,41],"sufficient":[15],"to":[16],"grasp":[17],"the":[18,63,71,110],"nature":[19],"underlying":[21],"emotional":[22,68],"states.":[23],"Dialog":[24],"speech":[25],"provides":[26],"useful":[27],"information":[28],"about":[29],"context":[30,51,61,69],"that":[31],"explains":[32],"nuances":[33],"emotions":[35],"their":[37],"transitions.":[38],"Context":[39],"can":[40],"defined":[42],"on":[43,55,62,70,96,112],"different":[44],"levels;":[45],"this":[46,113],"paper":[47],"proposes":[48],"a":[49,89,108],"hierarchical":[50],"modelling":[52],"approach":[53],"based":[54],"RNN-LSTM":[56],"architecture,":[57],"which":[58],"models":[59],"acoustical":[60],"frame":[64],"level":[65],"partner's":[67],"dialog":[72],"level.":[73],"The":[74],"method":[75],"is":[76,115],"proved":[77],"effective":[78],"together":[79],"with":[80],"cross-corpus":[81],"training":[82],"setup":[83],"domain":[85],"adaptation":[86],"technique":[87],"set":[90],"speaker":[92],"independent":[93],"cross-validation":[94],"experiments":[95],"IEMOCAP":[97],"corpus":[98,114],"for":[99,117],"three":[100],"levels":[101],"activation":[103],"valence":[105],"classification.":[106],"As":[107],"result,":[109],"state-of-the-art":[111],"advanced":[116],"both":[118],"dimensions":[119],"using":[120],"only":[121],"acoustic":[122],"modality.":[123]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}