{"id":"https://openalex.org/W3015267357","doi":"https://doi.org/10.1109/icassp40776.2020.9054629","title":"Speech Emotion Recognition with Dual-Sequence LSTM Architecture","display_name":"Speech Emotion Recognition with Dual-Sequence LSTM Architecture","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015267357","doi":"https://doi.org/10.1109/icassp40776.2020.9054629","mag":"3015267357"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054629","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054629","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1910.08874","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108766872","display_name":"Jianyou Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jianyou Wang","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Duke University, Durham, NC, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Duke University, Durham, NC, USA","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062432859","display_name":"Michael Xue","orcid":null},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Xue","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Duke University, Durham, NC, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Duke University, Durham, NC, USA","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023835646","display_name":"Ryan Culhane","orcid":null},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ryan Culhane","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Duke University, Durham, NC, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Duke University, Durham, NC, USA","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044413037","display_name":"Enmao Diao","orcid":"https://orcid.org/0000-0002-9151-7990"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Enmao Diao","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Duke University, Durham, NC, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Duke University, Durham, NC, USA","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069838077","display_name":"Jie Ding","orcid":"https://orcid.org/0000-0002-3584-6140"},"institutions":[{"id":"https://openalex.org/I4210101327","display_name":"Twin Cities Orthopedics","ror":"https://ror.org/01en4s460","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210101327"]},{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jie Ding","raw_affiliation_strings":["School of Statistics, University of Minnesota Twin Cities, Minneapolis, MN, USA"],"affiliations":[{"raw_affiliation_string":"School of Statistics, University of Minnesota Twin Cities, Minneapolis, MN, USA","institution_ids":["https://openalex.org/I4210101327","https://openalex.org/I130238516"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020766546","display_name":"Vahid Tarokh","orcid":"https://orcid.org/0000-0003-2994-6302"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vahid Tarokh","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Duke University, Durham, NC, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Duke University, Durham, NC, USA","institution_ids":["https://openalex.org/I170897317"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5108766872"],"corresponding_institution_ids":["https://openalex.org/I170897317"],"apc_list":null,"apc_paid":null,"fwci":15.7511,"has_fulltext":false,"cited_by_count":146,"citation_normalized_percentile":{"value":0.99334971,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6474","last_page":"6478"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9997000098228455,"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":0.998199999332428,"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/spectrogram","display_name":"Spectrogram","score":0.8913801908493042},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7772278785705566},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.6934175491333008},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.689628005027771},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.540210485458374},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5172134637832642},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.49375876784324646},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41959571838378906},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.41216179728507996},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.33463361859321594}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8913801908493042},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7772278785705566},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.6934175491333008},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.689628005027771},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.540210485458374},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5172134637832642},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.49375876784324646},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41959571838378906},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.41216179728507996},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.33463361859321594},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054629","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054629","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1910.08874","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.08874","pdf_url":"https://arxiv.org/pdf/1910.08874","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1910.08874","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.08874","pdf_url":"https://arxiv.org/pdf/1910.08874","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":[{"id":"https://metadata.un.org/sdg/4","score":0.6499999761581421,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W855255571","https://openalex.org/W1685006559","https://openalex.org/W2064675550","https://openalex.org/W2125455772","https://openalex.org/W2146334809","https://openalex.org/W2170942820","https://openalex.org/W2396144419","https://openalex.org/W2625297138","https://openalex.org/W2747006787","https://openalex.org/W2747664154","https://openalex.org/W2889717020","https://openalex.org/W2936372954","https://openalex.org/W2937154351","https://openalex.org/W2939488497","https://openalex.org/W2939987519","https://openalex.org/W2940259008","https://openalex.org/W2951442257","https://openalex.org/W2962770129","https://openalex.org/W2963304263","https://openalex.org/W4302375066","https://openalex.org/W6623445213","https://openalex.org/W6701650085","https://openalex.org/W6755596326"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W4317383455","https://openalex.org/W2548511587","https://openalex.org/W4293232884","https://openalex.org/W2422472940","https://openalex.org/W2019475500","https://openalex.org/W2548162870","https://openalex.org/W2144773493","https://openalex.org/W2138847091"],"abstract_inverted_index":{"Speech":[0],"Emotion":[1],"Recognition":[2],"(SER)":[3],"has":[4],"emerged":[5],"as":[6,69,128,130],"a":[7,23,64,85,97,109],"critical":[8],"component":[9],"of":[10,14,88,100,106],"the":[11,60,74,89],"next":[12],"generation":[13],"human-machine":[15],"interfacing":[16],"technologies.":[17],"In":[18],"this":[19],"work,":[20],"we":[21],"propose":[22],"new":[24],"dual-level":[25],"model":[26,93],"that":[27,124],"predicts":[28],"emotions":[29],"based":[30],"on":[31,95],"both":[32],"MFCC":[33,47,61],"features":[34,48],"and":[35,49,102,118],"mel-spectrograms":[36,51,76],"produced":[37],"from":[38],"raw":[39],"audio":[40,131],"signals.":[41,132],"Each":[42],"utterance":[43],"is":[44,119],"preprocessed":[45],"into":[46],"two":[50,75],"at":[52],"different":[53],"time-frequency":[54],"resolutions.":[55],"A":[56],"standard":[57],"LSTM":[58,66,71],"processes":[59,73],"features,":[62],"while":[63],"novel":[65],"architecture,":[67],"denoted":[68],"Dual-Sequence":[70],"(DS-LSTM),":[72],"simultaneously.":[77],"The":[78],"outputs":[79],"are":[80],"later":[81],"averaged":[82],"to":[83],"produce":[84],"final":[86],"classification":[87],"utterance.":[90],"Our":[91],"proposed":[92],"achieves,":[94],"average,":[96],"weighted":[98],"accuracy":[99,105],"72.7%":[101],"an":[103],"unweighted":[104],"73.3%":[107],"-":[108,117],"6%":[110],"improvement":[111],"over":[112],"current":[113],"state-of-the-art":[114],"unimodal":[115],"models":[116,123],"comparable":[120],"with":[121],"multimodal":[122],"leverage":[125],"textual":[126],"information":[127],"well":[129]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":25},{"year":2024,"cited_by_count":32},{"year":2023,"cited_by_count":36},{"year":2022,"cited_by_count":25},{"year":2021,"cited_by_count":19},{"year":2020,"cited_by_count":8}],"updated_date":"2026-04-18T07:56:08.524223","created_date":"2025-10-10T00:00:00"}