{"id":"https://openalex.org/W2787584921","doi":"https://doi.org/10.1109/apsipa.2017.8282242","title":"Speech emotion recognition via ensembling neural networks","display_name":"Speech emotion recognition via ensembling neural networks","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2787584921","doi":"https://doi.org/10.1109/apsipa.2017.8282242","mag":"2787584921"},"language":"en","primary_location":{"id":"doi:10.1109/apsipa.2017.8282242","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2017.8282242","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5070380058","display_name":"Danqing Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]},{"id":"https://openalex.org/I4210096887","display_name":"HKUST Shenzhen Research Institute","ror":"https://ror.org/00sz56h79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I200769079","https://openalex.org/I20231570","https://openalex.org/I4210096887","https://openalex.org/I4210147811"]}],"countries":["CN","HK"],"is_corresponding":true,"raw_author_name":"Danqing Luo","raw_affiliation_strings":["ADSPLAB/ELIP, Peking University, Shenzhen, China","IMSL Shenzhen Key Lab, PKU-HKUST Shenzhen Hong Kong Institution"],"affiliations":[{"raw_affiliation_string":"ADSPLAB/ELIP, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"IMSL Shenzhen Key Lab, PKU-HKUST Shenzhen Hong Kong Institution","institution_ids":["https://openalex.org/I4210096887","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002795838","display_name":"Yuexian Zou","orcid":"https://orcid.org/0000-0001-9999-6140"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuexian Zou","raw_affiliation_strings":["ADSPLAB/ELIP, Peking University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"ADSPLAB/ELIP, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112133862","display_name":"Dongyan Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Dongyan Huang","raw_affiliation_strings":["Human Language Technology, Institute for Infocomm Research/A*Star, Singapore"],"affiliations":[{"raw_affiliation_string":"Human Language Technology, Institute for Infocomm Research/A*Star, Singapore","institution_ids":["https://openalex.org/I3005327000"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5070380058"],"corresponding_institution_ids":["https://openalex.org/I20231570","https://openalex.org/I4210096887","https://openalex.org/I889458895"],"apc_list":null,"apc_paid":null,"fwci":1.3057,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.82181029,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"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/T10860","display_name":"Speech and Audio Processing","score":0.9955999851226807,"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":0.9902999997138977,"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":0.8044561743736267},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.741584300994873},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.6766777038574219},{"id":"https://openalex.org/keywords/confusion","display_name":"Confusion","score":0.6273216009140015},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6197131276130676},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.611315131187439},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5690048336982727},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5253567099571228},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.5053958892822266},{"id":"https://openalex.org/keywords/confusion-matrix","display_name":"Confusion matrix","score":0.4703913927078247},{"id":"https://openalex.org/keywords/residual-neural-network","display_name":"Residual neural network","score":0.4587339460849762},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4375770390033722},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38794076442718506}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8044561743736267},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.741584300994873},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.6766777038574219},{"id":"https://openalex.org/C2781140086","wikidata":"https://www.wikidata.org/wiki/Q557945","display_name":"Confusion","level":2,"score":0.6273216009140015},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6197131276130676},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.611315131187439},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5690048336982727},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5253567099571228},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5053958892822266},{"id":"https://openalex.org/C138602881","wikidata":"https://www.wikidata.org/wiki/Q2709591","display_name":"Confusion matrix","level":2,"score":0.4703913927078247},{"id":"https://openalex.org/C2944601119","wikidata":"https://www.wikidata.org/wiki/Q43744058","display_name":"Residual neural network","level":3,"score":0.4587339460849762},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4375770390033722},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38794076442718506},{"id":"https://openalex.org/C11171543","wikidata":"https://www.wikidata.org/wiki/Q41630","display_name":"Psychoanalysis","level":1,"score":0.0},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipa.2017.8282242","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2017.8282242","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4399999976158142,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1552624648","https://openalex.org/W1844030040","https://openalex.org/W2010520781","https://openalex.org/W2064675550","https://openalex.org/W2087618018","https://openalex.org/W2093174546","https://openalex.org/W2111926505","https://openalex.org/W2137639365","https://openalex.org/W2154024118","https://openalex.org/W2194775991","https://openalex.org/W2295001676","https://openalex.org/W2401231614","https://openalex.org/W2408520939","https://openalex.org/W2625297138","https://openalex.org/W2964137095"],"related_works":["https://openalex.org/W4298287631","https://openalex.org/W2953061907","https://openalex.org/W3032952384","https://openalex.org/W3034302643","https://openalex.org/W4366202965","https://openalex.org/W1969293528","https://openalex.org/W2349679704","https://openalex.org/W4389633859","https://openalex.org/W2570625548","https://openalex.org/W4386474889"],"abstract_inverted_index":{"Deep":[0],"Neural":[1,113],"Network":[2,114],"(DNN)":[3],"based":[4,150],"speech":[5,64,118],"emotion":[6,49,65],"recognition":[7],"(SER)":[8],"methods":[9,33],"have":[10],"demonstrated":[11],"competitive":[12],"performance":[13,110],"compared":[14],"to":[15,72],"traditional":[16],"SER":[17,32,96,143,151],"approaches.":[18],"However,":[19],"from":[20,51,100],"literatures,":[21],"it":[22],"can":[23],"be":[24,69],"seen":[25],"that":[26,39,56,139],"the":[27,76,82,108,146],"confusion":[28],"matrices":[29],"of":[30,46,78,86,111],"different":[31,40,44,48,117],"varied":[34],"a":[35],"lot,":[36],"which":[37,67],"indicates":[38],"DNN":[41],"architecture":[42],"has":[43],"capability":[45],"modeling":[47],"cues":[50],"speech.":[52],"It":[53],"also":[54],"means":[55],"single":[57,148],"classifier":[58],"hardly":[59],"performs":[60],"well":[61],"on":[62],"all":[63],"categories,":[66],"may":[68],"possibly":[70],"due":[71],"data":[73],"imbalance":[74],"and":[75,120,131],"limitation":[77],"classifier.":[79],"Motivated":[80],"by":[81],"improved":[83],"research":[84],"results":[85,99],"ensemble":[87,93,142],"learning,":[88],"this":[89,105],"paper":[90],"investigates":[91],"an":[92],"method":[94],"for":[95],"via":[97],"aggregating":[98],"several":[101],"base":[102,135],"classifiers.":[103,136],"In":[104],"study,":[106],"considering":[107],"outstanding":[109],"Recurrent":[112],"(RNN)":[115],"in":[116,124],"tasks":[119],"Residual":[121],"network":[122],"(ResNet)":[123],"image":[125],"related":[126],"classification,":[127],"we":[128],"chose":[129],"RNN":[130],"ResNet":[132],"acting":[133],"as":[134],"Experiments":[137],"show":[138],"our":[140],"proposed":[141],"system":[144],"outperforms":[145],"state-of-art":[147],"classifier-":[149],"system.":[152]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}