{"id":"https://openalex.org/W2038322938","doi":"https://doi.org/10.1109/icassp.2013.6638116","title":"A speech emotion recognition framework based on latent Dirichlet allocation: Algorithm and FPGA implementation","display_name":"A speech emotion recognition framework based on latent Dirichlet allocation: Algorithm and FPGA implementation","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2038322938","doi":"https://doi.org/10.1109/icassp.2013.6638116","mag":"2038322938"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6638116","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-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/A5110071946","display_name":"Mohit Shah","orcid":null},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"funder","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohit Shah","raw_affiliation_strings":["Sch. of Electr., Arizona State Univ., Tempe, AZ, USA"],"affiliations":[{"raw_affiliation_string":"Sch. of Electr., Arizona State Univ., Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103447849","display_name":"Lifeng Miao","orcid":null},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"funder","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lifeng Miao","raw_affiliation_strings":["Sch. of Electr., Arizona State Univ., Tempe, AZ, USA"],"affiliations":[{"raw_affiliation_string":"Sch. of Electr., Arizona State Univ., Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025336372","display_name":"Chaitali Chakrabarti","orcid":"https://orcid.org/0000-0002-9859-7778"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"funder","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chaitali Chakrabarti","raw_affiliation_strings":["Sch. of Electr., Arizona State Univ., Tempe, AZ, USA"],"affiliations":[{"raw_affiliation_string":"Sch. of Electr., Arizona State Univ., Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074371899","display_name":"Andreas Spanias","orcid":"https://orcid.org/0000-0003-0306-9348"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"funder","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andreas Spanias","raw_affiliation_strings":["Sch. of Electr., Arizona State Univ., Tempe, AZ, USA"],"affiliations":[{"raw_affiliation_string":"Sch. of Electr., Arizona State Univ., Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.031,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":22,"citation_normalized_percentile":{"value":0.728093,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":91},"biblio":{"volume":null,"issue":null,"first_page":"2553","last_page":"2557"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9995,"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":0.9995,"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":0.9989,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9962,"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/utterance","display_name":"Utterance","score":0.7084904}],"concepts":[{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.7755201},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7520546},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7084904},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.697731},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5962405},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.5024338},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.44019476},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36153007},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35918063},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3564025},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.17449006},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6638116","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.51,"display_name":"Peace, justice, and strong institutions","id":"https://metadata.un.org/sdg/16"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":20,"referenced_works":["https://openalex.org/W175750906","https://openalex.org/W1880262756","https://openalex.org/W1964469912","https://openalex.org/W1986069783","https://openalex.org/W1988888548","https://openalex.org/W2059706055","https://openalex.org/W2062391442","https://openalex.org/W2086468861","https://openalex.org/W2099336098","https://openalex.org/W2111926505","https://openalex.org/W2112301665","https://openalex.org/W2115979064","https://openalex.org/W2137639365","https://openalex.org/W2158061940","https://openalex.org/W2158630797","https://openalex.org/W2161050705","https://openalex.org/W4237791300","https://openalex.org/W4252381709","https://openalex.org/W56071945","https://openalex.org/W88081813"],"related_works":["https://openalex.org/W4317422773","https://openalex.org/W4315588616","https://openalex.org/W3126382579","https://openalex.org/W3107650560","https://openalex.org/W2888805565","https://openalex.org/W2810542905","https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2129350855","https://openalex.org/W2038083449"],"abstract_inverted_index":{"In":[0,48],"this":[1,30],"paper,":[2],"we":[3,70],"present":[4],"a":[5,12,33,50,93,113],"speech-based":[6],"emotion":[7],"recognition":[8],"framework":[9],"based":[10],"on":[11,141],"latent":[13],"Dirichlet":[14],"allocation":[15],"model.":[16],"This":[17,85,130],"method":[18],"assumes":[19],"that":[20,110],"incoming":[21],"speech":[22,65,114],"frames":[23],"are":[24],"conditionally":[25],"independent":[26],"and":[27,108],"exchangeable.":[28],"While":[29],"leads":[31],"to":[32,41,79],"loss":[34],"of":[35,76,92,116,127,135],"temporal":[36,57],"structure,":[37],"it":[38],"is":[39,87],"able":[40],"capture":[42],"significant":[43],"statistical":[44],"information":[45],"between":[46],"frames.":[47],"contrast,":[49],"hidden":[51,82],"Markov":[52,83],"model-based":[53],"approach":[54,137],"captures":[55],"the":[56,62,90,101,128,133],"structure":[58],"in":[59,96,112,122],"speech.":[60],"Using":[61],"German":[63],"emotional":[64],"database":[66],"EMO-DB":[67],"for":[68,81,138],"evaluation,":[69],"achieve":[71],"an":[72,105],"average":[73],"classification":[74],"accuracy":[75],"80.7%":[77],"compared":[78],"73%":[80],"models.":[84],"improvement":[86],"achieved":[88],"at":[89],"cost":[91],"slight":[94],"increase":[95],"computational":[97],"complexity.":[98],"We":[99],"map":[100],"proposed":[102],"algorithm":[103],"onto":[104],"FPGA":[106],"platform":[107],"show":[109],"emotions":[111],"utterance":[115],"duration":[117],"1.5s":[118],"can":[119],"be":[120],"identified":[121],"1.8ms,":[123],"while":[124],"utilizing":[125],"70%":[126],"resources.":[129],"further":[131],"demonstrates":[132],"suitability":[134],"our":[136],"real-time":[139],"applications":[140],"hand-held":[142],"devices.":[143]},"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2038322938","counts_by_year":[{"year":2022,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":5}],"updated_date":"2025-04-24T04:03:09.495071","created_date":"2016-06-24"}