{"id":"https://openalex.org/W1507741742","doi":"https://doi.org/10.1631/fitee.1400323","title":"Speech emotion recognition with unsupervised feature learning","display_name":"Speech emotion recognition with unsupervised feature learning","publication_year":2015,"publication_date":"2015-05-01","ids":{"openalex":"https://openalex.org/W1507741742","doi":"https://doi.org/10.1631/fitee.1400323","mag":"1507741742"},"language":"en","primary_location":{"id":"doi:10.1631/fitee.1400323","is_oa":false,"landing_page_url":"https://doi.org/10.1631/fitee.1400323","pdf_url":null,"source":{"id":"https://openalex.org/S4210189857","display_name":"Frontiers of Information Technology & Electronic Engineering","issn_l":"2095-9184","issn":["2095-9184","2095-9230"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers of Information Technology & Electronic Engineering","raw_type":"journal-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/A5073031145","display_name":"Zheng-Wei Huang","orcid":"https://orcid.org/0000-0002-4190-8643"},"institutions":[{"id":"https://openalex.org/I115592961","display_name":"Jiangsu University","ror":"https://ror.org/03jc41j30","country_code":"CN","type":"education","lineage":["https://openalex.org/I115592961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng-wei Huang","raw_affiliation_strings":["Department of Computer Science and Communication Engineering, Jiangsu University, Zhenjiang, 212013, China","Jiangsu University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Communication Engineering, Jiangsu University, Zhenjiang, 212013, China","institution_ids":["https://openalex.org/I115592961"]},{"raw_affiliation_string":"Jiangsu University","institution_ids":["https://openalex.org/I115592961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109377553","display_name":"Wentao Xue","orcid":null},"institutions":[{"id":"https://openalex.org/I115592961","display_name":"Jiangsu University","ror":"https://ror.org/03jc41j30","country_code":"CN","type":"education","lineage":["https://openalex.org/I115592961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen-tao Xue","raw_affiliation_strings":["Department of Computer Science and Communication Engineering, Jiangsu University, Zhenjiang, 212013, China","Jiangsu University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Communication Engineering, Jiangsu University, Zhenjiang, 212013, China","institution_ids":["https://openalex.org/I115592961"]},{"raw_affiliation_string":"Jiangsu University","institution_ids":["https://openalex.org/I115592961"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068470372","display_name":"Qirong Mao","orcid":"https://orcid.org/0000-0002-0616-4431"},"institutions":[{"id":"https://openalex.org/I115592961","display_name":"Jiangsu University","ror":"https://ror.org/03jc41j30","country_code":"CN","type":"education","lineage":["https://openalex.org/I115592961"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qi-rong Mao","raw_affiliation_strings":["Department of Computer Science and Communication Engineering, Jiangsu University, Zhenjiang, 212013, China","Jiangsu University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Communication Engineering, Jiangsu University, Zhenjiang, 212013, China","institution_ids":["https://openalex.org/I115592961"]},{"raw_affiliation_string":"Jiangsu University","institution_ids":["https://openalex.org/I115592961"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5068470372"],"corresponding_institution_ids":["https://openalex.org/I115592961"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":null,"fwci":3.0974,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":{"value":0.90200887,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"16","issue":"5","first_page":"358","last_page":"366"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9998000264167786,"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":0.9998000264167786,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music 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":0.7637523412704468},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6326259970664978},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5824161171913147},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.5798333287239075},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5377322435379028},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.5318666696548462},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5096104145050049},{"id":"https://openalex.org/keywords/restricted-boltzmann-machine","display_name":"Restricted Boltzmann machine","score":0.5071096420288086},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.5062138438224792},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49862241744995117},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.46836745738983154},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.46114808320999146},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.453741192817688},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44198933243751526},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38313430547714233},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3696943521499634}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7637523412704468},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6326259970664978},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5824161171913147},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.5798333287239075},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5377322435379028},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.5318666696548462},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5096104145050049},{"id":"https://openalex.org/C199354608","wikidata":"https://www.wikidata.org/wiki/Q7316287","display_name":"Restricted Boltzmann machine","level":3,"score":0.5071096420288086},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.5062138438224792},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49862241744995117},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.46836745738983154},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.46114808320999146},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.453741192817688},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44198933243751526},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38313430547714233},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3696943521499634},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1631/fitee.1400323","is_oa":false,"landing_page_url":"https://doi.org/10.1631/fitee.1400323","pdf_url":null,"source":{"id":"https://openalex.org/S4210189857","display_name":"Frontiers of Information Technology & Electronic Engineering","issn_l":"2095-9184","issn":["2095-9184","2095-9230"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers of Information Technology & Electronic Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5708410550","display_name":"\u57fa\u4e8e\u7a00\u758f\u8868\u793a\u548c\u8d85\u56fe\u7684\u89c6\u9891\u4e8b\u4ef6\u8bed\u4e49\u5206\u6790\u65b9\u6cd5\u7814\u7a76","funder_award_id":"61170126","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8638435805","display_name":"\u57fa\u4e8e\u60c5\u611f\u4e0a\u4e0b\u6587\u7684\u89c6\u89c9\u8bed\u97f3\u591a\u6a21\u6001\u534f\u540c\u60c5\u611f\u5206\u6790\u65b9\u6cd5\u7814\u7a76","funder_award_id":"61272211","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W97657646","https://openalex.org/W165981754","https://openalex.org/W175750906","https://openalex.org/W1502836588","https://openalex.org/W1974032589","https://openalex.org/W1974470404","https://openalex.org/W1977876930","https://openalex.org/W1993882792","https://openalex.org/W1998808035","https://openalex.org/W2009059481","https://openalex.org/W2016661008","https://openalex.org/W2017154415","https://openalex.org/W2025905516","https://openalex.org/W2047337856","https://openalex.org/W2062118960","https://openalex.org/W2064641533","https://openalex.org/W2074788634","https://openalex.org/W2099767163","https://openalex.org/W2105700358","https://openalex.org/W2107789863","https://openalex.org/W2118858186","https://openalex.org/W2127902639","https://openalex.org/W2128171688","https://openalex.org/W2139427956","https://openalex.org/W2147768505","https://openalex.org/W2155273149","https://openalex.org/W2160815625","https://openalex.org/W2161073241","https://openalex.org/W2164186291","https://openalex.org/W2168465881","https://openalex.org/W2168692779","https://openalex.org/W2396589722","https://openalex.org/W2597289420","https://openalex.org/W3102431071","https://openalex.org/W6600208142","https://openalex.org/W6601597184"],"related_works":["https://openalex.org/W2159052453","https://openalex.org/W3088732000","https://openalex.org/W2145836866","https://openalex.org/W2983142544","https://openalex.org/W2891059443","https://openalex.org/W4281663961","https://openalex.org/W3208888551","https://openalex.org/W4313561566","https://openalex.org/W3208386644","https://openalex.org/W4220682630"],"abstract_inverted_index":{"Emotion-based":[0],"features":[1,23,59],"are":[2],"critical":[3],"for":[4,56],"achieving":[5],"high":[6],"performance":[7,72,129],"in":[8,89],"a":[9,79,132],"speech":[10,65],"emotion":[11,66],"recognition":[12],"(SER)":[13],"system.":[14],"In":[15,31],"general,":[16],"it":[17],"is":[18],"difficult":[19],"to":[20,25,64,116,131],"develop":[21],"these":[22],"due":[24],"the":[26,29,45,71,74,83,90,93,98,123],"ambiguity":[27],"of":[28,73,82,85,100],"ground-truth.":[30],"this":[32],"paper,":[33],"we":[34],"apply":[35],"several":[36],"unsupervised":[37],"feature":[38],"learning":[39,57],"algorithms":[40],"(including":[41],"K":[42],"-means":[43],"clustering,":[44],"sparse":[46,49],"auto-encoder,":[47],"and":[48,77,97,111],"restricted":[50],"Boltzmann":[51],"machines),":[52],"which":[53],"have":[54],"promise":[55],"task-related":[58],"by":[60],"using":[61],"unlabeled":[62],"data,":[63],"recognition.":[67],"We":[68,119],"then":[69],"evaluate":[70],"proposed":[75],"approach":[76],"present":[78],"detailed":[80],"analysis":[81],"effect":[84],"two":[86],"important":[87],"factors":[88],"model":[91],"setup,":[92],"content":[94,109],"window":[95],"size":[96],"number":[99],"hidden":[101,113],"layer":[102],"nodes.":[103],"Experimental":[104],"results":[105],"show":[106,121],"that":[107,122],"larger":[108],"windows":[110],"more":[112],"nodes":[114],"contribute":[115],"higher":[117],"performance.":[118],"also":[120],"two-layer":[124],"network":[125],"cannot":[126],"explicitly":[127],"improve":[128],"compared":[130],"single-layer":[133],"network.":[134]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":2}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}