{"id":"https://openalex.org/W2795642794","doi":"https://doi.org/10.21437/interspeech.2018-1568","title":"Variational Autoencoders for Learning Latent Representations of Speech Emotion: A Preliminary Study","display_name":"Variational Autoencoders for Learning Latent Representations of Speech Emotion: A Preliminary Study","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2795642794","doi":"https://doi.org/10.21437/interspeech.2018-1568","mag":"2795642794"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-1568","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1568","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1712.08708","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047197696","display_name":"Siddique Latif","orcid":"https://orcid.org/0000-0001-5662-4777"},"institutions":[{"id":"https://openalex.org/I1323252656","display_name":"Information Technology University","ror":"https://ror.org/00ngv8j44","country_code":"PK","type":"education","lineage":["https://openalex.org/I1323252656"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Siddique Latif","raw_affiliation_strings":["[Information Technology University]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"[Information Technology University]","institution_ids":["https://openalex.org/I1323252656"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080929578","display_name":"Rajib Rana","orcid":"https://orcid.org/0000-0002-0506-2409"},"institutions":[{"id":"https://openalex.org/I185523456","display_name":"University of Southern Queensland","ror":"https://ror.org/04sjbnx57","country_code":"AU","type":"education","lineage":["https://openalex.org/I185523456"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Rajib Rana","raw_affiliation_strings":["[University of Southern Queensland]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"[University of Southern Queensland]","institution_ids":["https://openalex.org/I185523456"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037574053","display_name":"Junaid Qadir","orcid":"https://orcid.org/0000-0001-9466-2475"},"institutions":[{"id":"https://openalex.org/I1323252656","display_name":"Information Technology University","ror":"https://ror.org/00ngv8j44","country_code":"PK","type":"education","lineage":["https://openalex.org/I1323252656"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Junaid Qadir","raw_affiliation_strings":["[Information Technology University]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"[Information Technology University]","institution_ids":["https://openalex.org/I1323252656"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030922449","display_name":"Julien Epps","orcid":"https://orcid.org/0000-0001-6624-5551"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Julien Epps","raw_affiliation_strings":["University of New South Wales,#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of New South Wales,#TAB#","institution_ids":["https://openalex.org/I31746571"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3107","last_page":"3111"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9988999962806702,"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"}},"topics":[{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9988999962806702,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.998199999332428,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music 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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7988304495811462},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6754393577575684},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.6520640254020691},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6155821681022644},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5715664625167847},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5480185151100159},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5357128381729126},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5114768743515015},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.41757622361183167},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39402106404304504},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3926342725753784},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3856322169303894},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3483829200267792}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7988304495811462},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6754393577575684},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.6520640254020691},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6155821681022644},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5715664625167847},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5480185151100159},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5357128381729126},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5114768743515015},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.41757622361183167},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39402106404304504},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3926342725753784},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3856322169303894},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3483829200267792},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.21437/interspeech.2018-1568","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1568","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1712.08708","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1712.08708","pdf_url":"https://arxiv.org/pdf/1712.08708","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:eprints.usq.edu.au:35635","is_oa":false,"landing_page_url":"http://eprints.usq.edu.au/35635/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400692","display_name":"University of Southern Queensland ePrints (University of Southern Queensland)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I185523456","host_organization_name":"University of Southern Queensland","host_organization_lineage":["https://openalex.org/I185523456"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item (Commonwealth Reporting Category E)"},{"id":"doi:10.48550/arxiv.1712.08708","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1712.08708","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"mag:2795642794","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1712.08708","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1712.08708","pdf_url":"https://arxiv.org/pdf/1712.08708","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320335344","display_name":"Advance Queensland","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2795642794.pdf","grobid_xml":"https://content.openalex.org/works/W2795642794.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W648143168","https://openalex.org/W1412878278","https://openalex.org/W1522301498","https://openalex.org/W1964757081","https://openalex.org/W1995562189","https://openalex.org/W2050752817","https://openalex.org/W2099471712","https://openalex.org/W2146334809","https://openalex.org/W2149940198","https://openalex.org/W2161459043","https://openalex.org/W2173520492","https://openalex.org/W2202109488","https://openalex.org/W2239141610","https://openalex.org/W2295001676","https://openalex.org/W2343758848","https://openalex.org/W2399733683","https://openalex.org/W2408520939","https://openalex.org/W2467604901","https://openalex.org/W2515020857","https://openalex.org/W2528578439","https://openalex.org/W2532494225","https://openalex.org/W2583743457","https://openalex.org/W2586291442","https://openalex.org/W2586950923","https://openalex.org/W2605762339","https://openalex.org/W2607071059","https://openalex.org/W2746521834","https://openalex.org/W2748466034","https://openalex.org/W2761514455","https://openalex.org/W2951004968","https://openalex.org/W2962736520","https://openalex.org/W2963130397","https://openalex.org/W2963135265"],"related_works":["https://openalex.org/W2963087613","https://openalex.org/W2951004968","https://openalex.org/W2146334809","https://openalex.org/W3160016904","https://openalex.org/W2899929048","https://openalex.org/W2936173226","https://openalex.org/W2997887270","https://openalex.org/W2099471712","https://openalex.org/W1522301498","https://openalex.org/W3012461129","https://openalex.org/W2986154062","https://openalex.org/W3091189975","https://openalex.org/W2009059481","https://openalex.org/W2951123823","https://openalex.org/W2181990753","https://openalex.org/W2958208506","https://openalex.org/W2963131709","https://openalex.org/W2774085128","https://openalex.org/W2939224318","https://openalex.org/W2804753883"],"abstract_inverted_index":{"Learning":[0],"the":[1,20,91,105,112,123],"latent":[2,92],"representation":[3,93,100],"of":[4,22,94,107],"data":[5],"in":[6,56,60],"unsupervised":[7],"fashion":[8],"is":[9,33],"a":[10,23],"very":[11],"interesting":[12],"process":[13],"that":[14,127],"provides":[15],"relevant":[16],"features":[17,32,37,46,79,128],"for":[18,41,77,80,89,117,136],"enhancing":[19],"performance":[21],"classifier.":[24],"For":[25],"speech":[26,42,95,118,137],"emotion":[27,43,119,138],"recognition":[28],"tasks,":[29],"generating":[30,78],"effective":[31],"crucial.":[34],"Currently,":[35],"handcrafted":[36],"are":[38,111],"mostly":[39],"used":[40],"recognition,":[44],"however,":[45],"learned":[47,129],"automatically":[48],"using":[49],"deep":[50,65],"learning":[51],"have":[52,73],"shown":[53],"strong":[54],"success":[55,76],"many":[57],"problems,":[58],"especially":[59],"image":[61],"processing.":[62],"In":[63],"particular,":[64],"generative":[66],"models":[67],"such":[68],"as":[69],"Variational":[70],"Autoencoders":[71],"(VAEs)":[72],"gained":[74],"enormous":[75],"natural":[81],"images.":[82],"Inspired":[83],"by":[84,130],"this,":[85],"we":[86,110],"propose":[87,115],"VAEs":[88,116,131],"deriving":[90],"signals":[96],"and":[97],"use":[98],"this":[99],"to":[101,114],"classify":[102],"emotions.":[103],"To":[104],"best":[106],"our":[108],"knowledge,":[109],"first":[113],"classification.":[120,139],"Evaluations":[121],"on":[122],"IEMOCAP":[124],"dataset":[125],"demonstrate":[126],"can":[132],"produce":[133],"state-of-the-art":[134],"results":[135]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}