{"id":"https://openalex.org/W2930753566","doi":"https://doi.org/10.21437/interspeech.2019-3252","title":"Direct Modelling of Speech Emotion from Raw Speech","display_name":"Direct Modelling of Speech Emotion from Raw Speech","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2930753566","doi":"https://doi.org/10.21437/interspeech.2019-3252","mag":"2930753566"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-3252","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-3252","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1904.03833","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/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":true,"raw_author_name":"Siddique Latif","raw_affiliation_strings":["[University of Southern Queensland]"],"affiliations":[{"raw_affiliation_string":"[University of Southern Queensland]","institution_ids":["https://openalex.org/I185523456"]}]},{"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, Toowoomba, Australia"],"affiliations":[{"raw_affiliation_string":"University of Southern Queensland, Toowoomba, Australia","institution_ids":["https://openalex.org/I185523456"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064983246","display_name":"Sara Khalifa","orcid":"https://orcid.org/0000-0002-3417-2834"},"institutions":[{"id":"https://openalex.org/I4210101388","display_name":"Health Sciences and Nutrition","ror":"https://ror.org/0152bt112","country_code":"AU","type":"facility","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4210101388","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"funder","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Sara Khalifa","raw_affiliation_strings":["Commonwealth Scientific and Industrial Research Organisation, Canberra, Australia"],"affiliations":[{"raw_affiliation_string":"Commonwealth Scientific and Industrial Research Organisation, Canberra, Australia","institution_ids":["https://openalex.org/I4210101388","https://openalex.org/I1292875679"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088135082","display_name":"Raja Jurdak","orcid":"https://orcid.org/0000-0001-7517-0782"},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"funder","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I4210101388","display_name":"Health Sciences and Nutrition","ror":"https://ror.org/0152bt112","country_code":"AU","type":"facility","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4210101388","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Raja Jurdak","raw_affiliation_strings":["Commonwealth Scientific and Industrial Research Organisation, Canberra, Australia"],"affiliations":[{"raw_affiliation_string":"Commonwealth Scientific and Industrial Research Organisation, Canberra, Australia","institution_ids":["https://openalex.org/I4210101388","https://openalex.org/I1292875679"]}]},{"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":["UNSW Sydney, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"UNSW Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I31746571"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5047197696"],"corresponding_institution_ids":["https://openalex.org/I185523456"],"apc_list":null,"apc_paid":null,"fwci":3.8516,"has_fulltext":true,"cited_by_count":23,"citation_normalized_percentile":{"value":0.94364391,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3920","last_page":"3924"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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/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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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/computer-science","display_name":"Computer science","score":0.8230370283126831},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6863946914672852},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5645020008087158},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5367324352264404},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5251742601394653},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.49411657452583313},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.4785221815109253},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4524936378002167},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.451903760433197},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4295847713947296},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4245138168334961},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.41350629925727844}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8230370283126831},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6863946914672852},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5645020008087158},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5367324352264404},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5251742601394653},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.49411657452583313},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.4785221815109253},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4524936378002167},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.451903760433197},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4295847713947296},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4245138168334961},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.41350629925727844},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.21437/interspeech.2019-3252","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-3252","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1904.03833","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.03833","pdf_url":"https://arxiv.org/pdf/1904.03833","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":"","raw_type":null},{"id":"mag:2930753566","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1904.03833","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:eprints.usq.edu.au:37149","is_oa":false,"landing_page_url":"http://eprints.usq.edu.au/37149/","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.1904.03833","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1904.03833","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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1904.03833","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.03833","pdf_url":"https://arxiv.org/pdf/1904.03833","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":"","raw_type":null},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4000000059604645,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2930753566.pdf","grobid_xml":"https://content.openalex.org/works/W2930753566.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W1600744878","https://openalex.org/W1677182931","https://openalex.org/W2045528981","https://openalex.org/W2059652044","https://openalex.org/W2064675550","https://openalex.org/W2090777335","https://openalex.org/W2146334809","https://openalex.org/W2148154194","https://openalex.org/W2168249605","https://openalex.org/W2239141610","https://openalex.org/W2342475039","https://openalex.org/W2398826216","https://openalex.org/W2399733683","https://openalex.org/W2407080277","https://openalex.org/W2408449330","https://openalex.org/W2508048623","https://openalex.org/W2529337537","https://openalex.org/W2570412145","https://openalex.org/W2586291442","https://openalex.org/W2648194195","https://openalex.org/W2766272105","https://openalex.org/W2766421188","https://openalex.org/W2770454110","https://openalex.org/W2785711646","https://openalex.org/W2803098682","https://openalex.org/W2804483946","https://openalex.org/W2889191349","https://openalex.org/W2892071465","https://openalex.org/W2903799412","https://openalex.org/W2917446798","https://openalex.org/W2949117887","https://openalex.org/W2951442257","https://openalex.org/W2963083845","https://openalex.org/W2963087613"],"related_works":["https://openalex.org/W2973037561","https://openalex.org/W2146334809","https://openalex.org/W175750906","https://openalex.org/W2399733683","https://openalex.org/W2239141610","https://openalex.org/W2912728762","https://openalex.org/W2897132394","https://openalex.org/W3166052096","https://openalex.org/W3204087964","https://openalex.org/W3115394420","https://openalex.org/W3114531069","https://openalex.org/W2997026866","https://openalex.org/W2295001676","https://openalex.org/W2610961739","https://openalex.org/W2536944292","https://openalex.org/W2917446798","https://openalex.org/W2087618018","https://openalex.org/W1501669607","https://openalex.org/W3095648847","https://openalex.org/W2281407413"],"abstract_inverted_index":{"Speech":[0],"emotion":[1,55,106,139,185],"recognition":[2,140,186],"is":[3,30,35,52,174],"a":[4,26,44,77],"challenging":[5],"task":[6],"and":[7,84,108,208],"heavily":[8],"depends":[9],"on":[10],"hand-engineered":[11,203],"acoustic":[12],"features,":[13],"which":[14],"are":[15,131],"typically":[16],"crafted":[17],"to":[18,39,115,134,163],"echo":[19],"human":[20],"perception":[21],"of":[22,63,79,98,120,138,149,159,199],"speech":[23,68,144],"signals.":[24],"However,":[25],"filter":[27],"bank":[28],"that":[29,129,173,191],"designed":[31],"from":[32,66,141,205],"perceptual":[33],"evidence":[34],"not":[36],"always":[37],"guaranteed":[38],"be":[40],"the":[41,49,60,95,117,136,142,147,157,169,178,184,192,197],"best":[42],"in":[43,100,151,168],"statistical":[45],"modelling":[46,152],"framework":[47],"where":[48],"end":[50],"goal":[51],"for":[53,94,105,112,183],"example":[54],"classification.":[56],"This":[57],"has":[58],"fuelled":[59],"emerging":[61],"trend":[62],"learning":[64,72,101],"representations":[65],"raw":[67,143],"especially":[69],"using":[70],"deep":[71],"neural":[73,122],"networks.":[74,123],"In":[75,124],"particular,":[76],"combination":[78],"Convolution":[80],"Neural":[81],"Networks":[82],"(CNNs)":[83],"Long":[85],"Short":[86],"Term":[87],"Memory":[88],"(LSTM)":[89],"have":[90],"gained":[91],"great":[92],"traction":[93],"intrinsic":[96],"property":[97],"LSTM":[99,179],"contextual":[102,153],"information":[103],"crucial":[104],"recognition;":[107],"CNNs":[109],"been":[110],"used":[111],"its":[113],"ability":[114],"overcome":[116],"scalability":[118],"problem":[119],"regular":[121],"this":[125],"paper,":[126],"we":[127],"show":[128],"there":[130],"still":[132],"opportunities":[133],"improve":[135],"performance":[137,198],"by":[145],"exploiting":[146],"properties":[148],"CNN":[150,200],"information.":[154],"We":[155],"propose":[156],"use":[158],"parallel":[160],"convolutional":[161],"layers":[162],"harness":[164],"multiple":[165],"temporal":[166],"resolutions":[167],"feature":[170],"extraction":[171],"block":[172],"jointly":[175],"trained":[176,201],"with":[177,202],"based":[180],"classification":[181],"network":[182],"task.":[187],"Our":[188],"results":[189],"suggest":[190],"proposed":[193],"model":[194],"can":[195],"reach":[196],"features":[204],"both":[206],"IEMOCAP":[207],"MSP-IMPROV":[209],"datasets.":[210]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":3}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}