{"id":"https://openalex.org/W2801959488","doi":"https://doi.org/10.1109/icassp.2018.8461299","title":"Soft-Target Training with Ambiguous Emotional Utterances for DNN-Based Speech Emotion Classification","display_name":"Soft-Target Training with Ambiguous Emotional Utterances for DNN-Based Speech Emotion Classification","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2801959488","doi":"https://doi.org/10.1109/icassp.2018.8461299","mag":"2801959488"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461299","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461299","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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/A5061074419","display_name":"Atsushi Ando","orcid":"https://orcid.org/0000-0002-3971-0654"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Atsushi Ando","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024724493","display_name":"Satoshi Kobashikawa","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Kobashikawa","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043775847","display_name":"Hosana Kamiyama","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hosana Kamiyama","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060644399","display_name":"Ryo Masumura","orcid":"https://orcid.org/0000-0002-2415-4149"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryo Masumura","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068604686","display_name":"Yusuke Ijima","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yusuke Ijima","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067237053","display_name":"Yushi Aono","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yushi Aono","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":45,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4964","last_page":"4968"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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":0.9979000091552734,"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":0.9958000183105469,"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":0.7913234233856201},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6868986487388611},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.5958377718925476},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5509025454521179},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5328942537307739},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4847938120365143},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4692309498786926},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36792030930519104},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33427613973617554}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7913234233856201},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6868986487388611},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5958377718925476},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5509025454521179},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5328942537307739},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4847938120365143},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4692309498786926},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36792030930519104},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33427613973617554},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","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.2018.8461299","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461299","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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","id":"https://metadata.un.org/sdg/4","score":0.5899999737739563}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W257874415","https://openalex.org/W1821462560","https://openalex.org/W2074788634","https://openalex.org/W2085662862","https://openalex.org/W2136705941","https://openalex.org/W2146334809","https://openalex.org/W2154780170","https://openalex.org/W2170876097","https://openalex.org/W2295001676","https://openalex.org/W2408520939","https://openalex.org/W2512885694","https://openalex.org/W2552810951","https://openalex.org/W2625297138","https://openalex.org/W4245744384","https://openalex.org/W6609695107","https://openalex.org/W6680499999","https://openalex.org/W6683465724","https://openalex.org/W6685269245","https://openalex.org/W6697498398","https://openalex.org/W6714031499","https://openalex.org/W6730005429"],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W3216976533","https://openalex.org/W4394050964","https://openalex.org/W3126677997","https://openalex.org/W1610857240","https://openalex.org/W2551249631"],"abstract_inverted_index":{"This":[0],"paper":[1,41,77],"presents":[2],"a":[3],"novel":[4],"emotion":[5,53],"classification":[6],"method":[7,18,66,98],"for":[8,62],"natural":[9],"speech.":[10],"One":[11],"of":[12,28,104],"the":[13,16,26,29,43,64,79,96],"problems":[14],"in":[15,82,102],"state-of-the-art":[17],"based":[19],"on":[20],"Deep":[21],"Neural":[22],"Network":[23],"(DNN)":[24],"is":[25],"paucity":[27],"training":[30,81],"data":[31],"compared":[32],"to":[33,84],"model":[34],"complexity.":[35],"To":[36],"solve":[37],"this":[38,40,76],"problem,":[39],"utilizes":[42],"ambiguous":[44,59,90],"emotional":[45,60,91],"utterances,":[46],"utterances":[47,61],"that":[48,95],"have":[49],"no":[50],"dominant":[51],"target":[52],"label.":[54],"While":[55],"previous":[56],"work":[57],"ignored":[58],"training,":[63],"proposed":[65,97],"leverages":[67],"all":[68],"annotated":[69],"labels":[70],"via":[71],"soft-target":[72,80],"training.":[73],"In":[74],"addition,":[75],"modifies":[78],"order":[83],"effectively":[85],"handle":[86],"both":[87,105],"clear":[88],"and":[89,107],"utterances.":[92],"Experiments":[93],"show":[94],"yields":[99],"performance":[100],"improvements":[101],"terms":[103],"weighted":[106],"unweighted":[108],"accuracies.":[109]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}