{"id":"https://openalex.org/W2889169802","doi":"https://doi.org/10.21437/interspeech.2018-2466","title":"Deep Neural Networks for Emotion Recognition Combining Audio and Transcripts","display_name":"Deep Neural Networks for Emotion Recognition Combining Audio and Transcripts","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2889169802","doi":"https://doi.org/10.21437/interspeech.2018-2466","mag":"2889169802"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-2466","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-2466","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":"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/A5059500729","display_name":"Jaejin Cho","orcid":"https://orcid.org/0000-0001-5672-6765"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jaejin Cho","raw_affiliation_strings":["Center for Language Speech Processing, Johns Hopkins University, Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"Center for Language Speech Processing, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040448607","display_name":"Raghavendra Pappagari","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Raghavendra Pappagari","raw_affiliation_strings":["Center for Language Speech Processing, Johns Hopkins University, Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"Center for Language Speech Processing, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088310443","display_name":"Purva Kulkarni","orcid":"https://orcid.org/0000-0002-4681-4582"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Purva Kulkarni","raw_affiliation_strings":["IntelligentWire, Seattle, WA, USA"],"affiliations":[{"raw_affiliation_string":"IntelligentWire, Seattle, WA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057010207","display_name":"Jes\u00fas Villalba","orcid":"https://orcid.org/0000-0001-9459-8426"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jes\u00fas Villalba","raw_affiliation_strings":["Center for Language Speech Processing, Johns Hopkins University, Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"Center for Language Speech Processing, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060644900","display_name":"Yishay Carmiel","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yishay Carmiel","raw_affiliation_strings":["IntelligentWire, Seattle, WA, USA"],"affiliations":[{"raw_affiliation_string":"IntelligentWire, Seattle, WA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050632169","display_name":"Najim Dehak","orcid":"https://orcid.org/0000-0002-4489-5753"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Najim Dehak","raw_affiliation_strings":["Center for Language Speech Processing, Johns Hopkins University, Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"Center for Language Speech Processing, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5059500729"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":12.6874,"has_fulltext":false,"cited_by_count":94,"citation_normalized_percentile":{"value":0.98907372,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"247","last_page":"251"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9954000115394592,"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":0.9954000115394592,"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":0.9947999715805054,"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":0.9922999739646912,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6925394535064697},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.667667806148529},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6044654846191406},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.5619584321975708},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4995143413543701},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4554668068885803}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6925394535064697},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.667667806148529},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6044654846191406},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5619584321975708},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4995143413543701},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4554668068885803}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2018-2466","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-2466","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6000000238418579,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1534131679","https://openalex.org/W1924770834","https://openalex.org/W2009059481","https://openalex.org/W2146334809","https://openalex.org/W2157364932","https://openalex.org/W2239141610","https://openalex.org/W2533262878","https://openalex.org/W2583643061","https://openalex.org/W2584561145","https://openalex.org/W2587150483","https://openalex.org/W2625297138","https://openalex.org/W2740550900","https://openalex.org/W2802103240"],"related_works":["https://openalex.org/W2386387936","https://openalex.org/W2778699561","https://openalex.org/W1629725936","https://openalex.org/W2785763105","https://openalex.org/W4233723219","https://openalex.org/W3126677997","https://openalex.org/W3142820373","https://openalex.org/W2357328515","https://openalex.org/W1573342376","https://openalex.org/W4224129546"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,85,145,153],"propose":[4],"to":[5,24,44,60,102,180],"improve":[6],"emotion":[7,26,46,88],"recognition":[8],"by":[9,167],"combining":[10],"acoustic":[11,28,183],"information":[12,63,163],"and":[13,96,161,172],"conversation":[14],"transcripts.On":[15],"the":[16,36,71,87,129,135,143,151,176],"one":[17],"hand,":[18,38],"a":[19,39,78,91,181],"LSTM":[20],"network":[21],"was":[22,42],"used":[23,43,146,154],"detect":[25,45],"from":[27,47,83,105,112],"features":[29,123],"like":[30],"f0,":[31],"shimmer,":[32],"jitter,":[33],"MFCC,":[34],"etc.On":[35],"other":[37],"multi-resolution":[40],"CNN":[41,50,118],"word":[48],"sequences.This":[49],"consists":[51],"of":[52,74,94,138],"several":[53],"parallel":[54],"convolutions":[55],"with":[56,119],"different":[57,65,75,113],"kernel":[58],"sizes":[59],"exploit":[61],"contextual":[62],"at":[64],"levels.A":[66],"temporal":[67],"pooling":[68],"layer":[69],"aggregates":[70],"hidden":[72],"representations":[73],"words":[76],"into":[77],"unique":[79],"sequence":[80],"level":[81],"embedding,":[82],"which":[84],"computed":[86],"posteriors.We":[89],"optimized":[90],"weighted":[92],"sum":[93],"classification":[95],"verification":[97,99],"losses.The":[98],"loss":[100],"tries":[101],"bring":[103],"embeddings":[104,111],"same":[106],"emotions":[107],"closer":[108],"while":[109,149],"separating":[110],"emotions.We":[114],"also":[115],"compared":[116,179],"our":[117,126],"state-of-the-art":[120],"text-based":[121],"hand-crafted":[122],"(e-vector).We":[124],"evaluated":[125],"approach":[127],"on":[128],"USC-IEMOCAP":[130],"dataset":[131,136],"as":[132,134],"well":[133],"consisting":[137],"US":[139],"English":[140],"telephone":[141,177],"speech.In":[142],"former,":[144],"human-annotated":[147],"transcripts":[148],"in":[150],"latter,":[152],"ASR":[155],"transcripts.The":[156],"results":[157],"showed":[158],"fusing":[159],"audio":[160],"transcript":[162],"improved":[164],"unweighted":[165],"accuracy":[166],"relative":[168,173],"24%":[169],"for":[170,175],"IEMOCAP":[171],"3.4%":[174],"data":[178],"single":[182],"system.":[184]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":21},{"year":2020,"cited_by_count":24},{"year":2019,"cited_by_count":14}],"updated_date":"2026-03-04T07:04:00.330322","created_date":"2025-10-10T00:00:00"}