{"id":"https://openalex.org/W24729848","doi":"https://doi.org/10.21437/interspeech.2009-585","title":"ANN based decision fusion for speech emotion recognition","display_name":"ANN based decision fusion for speech emotion recognition","publication_year":2009,"publication_date":"2009-09-06","ids":{"openalex":"https://openalex.org/W24729848","doi":"https://doi.org/10.21437/interspeech.2009-585","mag":"24729848"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2009-585","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-585","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","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/A5101578513","display_name":"Lu Xu","orcid":null},"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":"Lu Xu","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111983309","display_name":"Mingxing Xu","orcid":"https://orcid.org/0009-0000-3878-315X"},"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":"Mingxing Xu","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114013574","display_name":"Dali Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I78675632","display_name":"Beijing Information Science & Technology University","ror":"https://ror.org/04xnqep60","country_code":"CN","type":"education","lineage":["https://openalex.org/I78675632"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dali Yang","raw_affiliation_strings":["Beijing Information Science & Technology University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Information Science & Technology University, Beijing, China","institution_ids":["https://openalex.org/I78675632"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2035","last_page":"2038"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9922999739646912,"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/T10057","display_name":"Face and Expression Recognition","score":0.9901999831199646,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/speech-recognition","display_name":"Speech recognition","score":0.75145423412323},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7440082430839539},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.7079017162322998},{"id":"https://openalex.org/keywords/emotion-classification","display_name":"Emotion classification","score":0.5770792365074158},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.5214585661888123},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43524059653282166},{"id":"https://openalex.org/keywords/speech-analytics","display_name":"Speech analytics","score":0.4249677062034607},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4177594780921936},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37991249561309814},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.37552890181541443},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.2946728467941284},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08717206120491028}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.75145423412323},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7440082430839539},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7079017162322998},{"id":"https://openalex.org/C206310091","wikidata":"https://www.wikidata.org/wiki/Q750859","display_name":"Emotion classification","level":2,"score":0.5770792365074158},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5214585661888123},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43524059653282166},{"id":"https://openalex.org/C54953205","wikidata":"https://www.wikidata.org/wiki/Q4142201","display_name":"Speech analytics","level":4,"score":0.4249677062034607},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4177594780921936},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37991249561309814},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.37552890181541443},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.2946728467941284},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08717206120491028},{"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:10.21437/interspeech.2009-585","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-585","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6899999976158142}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1601061684","https://openalex.org/W1668904664","https://openalex.org/W1972280480","https://openalex.org/W1999377076","https://openalex.org/W2080853599","https://openalex.org/W2110052520","https://openalex.org/W2147634797","https://openalex.org/W2153457644","https://openalex.org/W2348059621","https://openalex.org/W2794807131","https://openalex.org/W2891601182","https://openalex.org/W2981666567","https://openalex.org/W3216401400"],"related_works":["https://openalex.org/W4281557318","https://openalex.org/W4308351423","https://openalex.org/W1550318927","https://openalex.org/W4305042383","https://openalex.org/W2546649374","https://openalex.org/W2773396412","https://openalex.org/W4380854332","https://openalex.org/W2184859701","https://openalex.org/W4380370144","https://openalex.org/W2009950829"],"abstract_inverted_index":{"Abstract":[0],"As":[1],"a":[2,23,109],"hot":[3],"research":[4],"field,":[5],"speech":[6,27,99,134,140,157,205,218,226,249,272,308,338,350,362,468,536],"emotion":[7,100,141,150,191,219,257,273,309,333,339,363,446,469,537],"recognition":[8,142,151,192,220,274,278,340,364,447,470,514,538],"has":[9,408],"attracted":[10],"increasing":[11,131],"attentions":[12],"from":[13,73],"both":[14,322],"academic":[15],"and":[16,31,90,114,120,126,145,155,176,183,187,209,243,264,275,387,414,448,515,548,556,573,586],"business.":[17],"In":[18,459,569,580],"this":[19,460,526],"paper,":[20,461],"we":[21],"proposed":[22,85,506,561],"method":[24,347,407],"to":[25,32,163,196,231,253,314,319,327,343,348,411,437,452,479,489],"recognize":[26,201,480],"emotions":[28,203],"adopting":[29,63],"ANNs":[30,430,442,476],"fuse":[33,321,490],"two":[34,323,493],"kinds":[35,224,324,494],"of":[36,58,70,133,169,174,181,217,225,325,332,337,441,495,511,525,546,575],"recognitions":[37,491],"using":[38,429,492],"different":[39,399,475],"features":[40,75,227,242,250,260,288,301,326,496,533],"at":[41,497],"the":[42,56,64,68,84,91,130,198,239,330,457,462,484,498,505,509],"decision":[43,86,103,465,499,562],"level.":[44,500],"Each":[45],"emotional":[46,295],"utterance":[47],"is":[48,76,88,94,108,116,152,221,312,341,435,443,450,528,564],"recognized":[49],"by":[50,207],"some":[51,211,418],"individual":[52],"recognizers":[53,60],"firstly.":[54],"Then":[55,483],"outputs":[57],"these":[59,300],"were":[61,251,477],"fused":[62],"voting":[65,485],"strategy.":[66],"Furthermore,":[67],"dimensionality":[69,92],"supervectors":[71],"constructed":[72],"spectral":[74,285],"reduced":[77],"through":[78],"PCA.":[79],"Experimental":[80,501],"results":[81,502,577],"demonstrated":[82,276,503],"that":[83,222,423,504],"fusion":[87,104,466,563],"effective":[89,121,291,317,346],"reduction":[93],"feasible.":[95],"Index":[96],"Terms":[97],":":[98],"recognition,":[101,310],"ANN,":[102],"1.":[105],"Introduction":[106],"Speech":[107,149,190],"dominant":[110],"tool":[111],"for":[112,123,256,293,361,445,467,535],"communication,":[113],"it":[115,311,434,449],"also":[117],"an":[118,153,316,345],"important":[119,147],"approach":[122,507],"transmitting":[124],"information":[125],"human":[127,233],"emotions.":[128,234,244,351,482],"With":[129,245],"role":[132],"interfaces":[135],"in":[136,204,271,307,541,553,566],"human-machine":[137],"interaction":[138],"applications,":[139],"becomes":[143],"more":[144,146],"recently.":[148],"interesting":[154],"challenging":[156],"technology,":[158],"which":[159,223,439],"can":[160,228],"be":[161,229,254,412,427],"applied":[162],"broad":[164],"areas,":[165],"such":[166,366],"as":[167,367,431,530],"environment":[168],"call":[170],"center":[171],"[1],":[172],"treatment":[173],"mental":[175],"psychological":[177],"diseases":[178],"[2],":[179],"development":[180],"education":[182],"entertainment":[184],"software":[185],"[3],":[186],"so":[188,388],"on.":[189,389],"deals":[193],"with":[194,400,456,520],"how":[195,342],"make":[197],"computer":[199],"automatically":[200],"various":[202,481],"signal":[206],"extracting":[208],"analyzing":[210],"acoustic":[212],"features.":[213],"A":[214],"key":[215,335],"problem":[216],"used":[230,255,270,360,478,534],"represent":[232],"Some":[235],"researchers":[236],"have":[237,267,303,358,421],"investigated":[238],"relations":[240],"between":[241],"their":[246,396],"efforts,":[247],"many":[248,354],"found":[252],"recognition.":[258],"Statistical":[259],"based":[261,406,464,513,522],"on":[262],"prosody":[263],"voice":[265],"quality":[266],"been":[268,359,409],"widely":[269],"considerable":[277],"success":[279],"[4,":[280],"5].":[281],"Besides":[282],"statistical":[283],"features,":[284],"or":[286],"cepstral":[287],"are":[289,392,398,539,550,578,584,589],"another":[290],"group":[292],"describing":[294],"states":[296],"[6,":[297],"7].":[298],"Since":[299],"all":[302,393],"played":[304],"significant":[305],"roles":[306],"necessary":[313,451],"explore":[315],"way":[318],"complementarily":[320],"further":[328],"enhance":[329],"performance":[331,425,455,510],"recognition.Another":[334],"issue":[336],"choose":[344],"classify":[349],"So":[352],"far,":[353],"pattern":[355],"classification":[356],"methods":[357,391],"[6-9],":[365],"Support":[368],"Vector":[369],"Machine":[370],"(SVM),":[371],"k-Nearest":[372],"Neighbors":[373],"(k-NN),":[374],"Gaussian":[375],"Mixture":[376],"Model":[377,381],"(GMM),":[378],"Hidden":[379],"Markov":[380],"(HMM),":[382],"Artificial":[383],"Neural":[384],"Networks":[385],"(ANN),":[386],"These":[390],"feasible,":[394],"but":[395],"performances":[397],"each":[401],"other":[402],"seriously.":[403],"The":[404,532,544,560],"SVMs":[405],"shown":[410],"robust":[413],"performs":[415],"well.":[416,432],"But":[417],"fresh":[419],"researches":[420],"indicated":[422],"ideal":[424],"may":[426],"obtained":[428],"However,":[433],"difficult":[436],"determine":[438],"kind":[440],"suitable":[444],"compare":[453],"its":[454,516],"SVMs.":[458],"ANN":[463,512,549],"was":[471,487,518],"presented.":[472,579],"Firstly":[473],"four":[474],"scheme":[486],"adopted":[488],"improved":[508],"accuracy":[517],"comparable":[519],"SVM":[521],"method.The":[523],"remainder":[524],"paper":[527],"organized":[529],"follows.":[531],"introduced":[540],"Section":[542,554,557,567,570,581],"2.":[543],"principles":[545],"PCA":[547],"briefly":[551],"described":[552],"3":[555],"4":[558],"respectively.":[559],"depicted":[565],"5.":[568],"6,":[571],"experiments":[572],"discussions":[574],"experimental":[576],"7,":[582],"conclusions":[583],"drawn":[585],"future":[587],"works":[588],"suggested.":[590]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}