{"id":"https://openalex.org/W2892071465","doi":"https://doi.org/10.1109/icassp.2018.8462677","title":"End-to-End Speech Emotion Recognition Using Deep Neural Networks","display_name":"End-to-End Speech Emotion Recognition Using Deep Neural Networks","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2892071465","doi":"https://doi.org/10.1109/icassp.2018.8462677","mag":"2892071465"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462677","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462677","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://opus.bibliothek.uni-augsburg.de/opus4/files/45054/45054.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045277971","display_name":"Panagiotis Tzirakis","orcid":"https://orcid.org/0000-0001-9449-5339"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Panagiotis Tzirakis","raw_affiliation_strings":["Department of Computing, Imperial College London, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing, Imperial College London, London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101678262","display_name":"Jiehao Zhang","orcid":"https://orcid.org/0000-0002-1159-9712"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jiehao Zhang","raw_affiliation_strings":["Department of Computing, Imperial College London, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing, Imperial College London, London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043060302","display_name":"Bj\u00f6rn W. Schuller","orcid":"https://orcid.org/0000-0002-6478-8699"},"institutions":[{"id":"https://openalex.org/I179225836","display_name":"University of Augsburg","ror":"https://ror.org/03p14d497","country_code":"DE","type":"education","lineage":["https://openalex.org/I179225836"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bjorn W. Schuller","raw_affiliation_strings":["Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Germany","institution_ids":["https://openalex.org/I179225836"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5045277971"],"corresponding_institution_ids":["https://openalex.org/I47508984"],"apc_list":null,"apc_paid":null,"fwci":24.9547,"has_fulltext":true,"cited_by_count":273,"citation_normalized_percentile":{"value":0.99683573,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"5089","last_page":"5093"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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":0.9986000061035156,"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/end-to-end-principle","display_name":"End-to-end principle","score":0.7743856906890869},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6862150430679321},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6671633124351501},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.5814372301101685},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5033690333366394},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32488498091697693}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7743856906890869},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6862150430679321},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6671633124351501},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5814372301101685},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5033690333366394},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32488498091697693}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2018.8462677","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462677","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:uni-augsburg.opus-bayern.de:45054","is_oa":true,"landing_page_url":"https://opus.bibliothek.uni-augsburg.de/opus4/frontdoor/index/index/docId/45054","pdf_url":"https://opus.bibliothek.uni-augsburg.de/opus4/files/45054/45054.pdf","source":{"id":"https://openalex.org/S4306400930","display_name":"OPUS (Augsburg University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119916105","host_organization_name":"Augsburg University","host_organization_lineage":["https://openalex.org/I119916105"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"bookpart"}],"best_oa_location":{"id":"pmh:oai:uni-augsburg.opus-bayern.de:45054","is_oa":true,"landing_page_url":"https://opus.bibliothek.uni-augsburg.de/opus4/frontdoor/index/index/docId/45054","pdf_url":"https://opus.bibliothek.uni-augsburg.de/opus4/files/45054/45054.pdf","source":{"id":"https://openalex.org/S4306400930","display_name":"OPUS (Augsburg University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119916105","host_organization_name":"Augsburg University","host_organization_lineage":["https://openalex.org/I119916105"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"bookpart"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2892071465.pdf","grobid_xml":"https://content.openalex.org/works/W2892071465.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W211912913","https://openalex.org/W1600744878","https://openalex.org/W1785074626","https://openalex.org/W2045528981","https://openalex.org/W2059652044","https://openalex.org/W2072803611","https://openalex.org/W2095705004","https://openalex.org/W2099767163","https://openalex.org/W2149628368","https://openalex.org/W2239141610","https://openalex.org/W2346454595","https://openalex.org/W2398826216","https://openalex.org/W2399733683","https://openalex.org/W2518110751","https://openalex.org/W2529337537","https://openalex.org/W2604268783","https://openalex.org/W2610961739","https://openalex.org/W2624578427","https://openalex.org/W2915606245","https://openalex.org/W2962736520","https://openalex.org/W6661966438","https://openalex.org/W6674330103","https://openalex.org/W6728126488","https://openalex.org/W6736078852","https://openalex.org/W6739373864"],"related_works":["https://openalex.org/W2151749779","https://openalex.org/W3179968364","https://openalex.org/W1999612375","https://openalex.org/W2938107654","https://openalex.org/W3008587939","https://openalex.org/W3196421258","https://openalex.org/W4387301579","https://openalex.org/W2763956190","https://openalex.org/W3126677997","https://openalex.org/W1610857240"],"abstract_inverted_index":{"Affect":[0],"recognition":[1,17,61],"is":[2,70],"an":[3],"important":[4],"component":[5],"towards":[6],"the":[7,82,101,105,117,121],"better":[8],"interaction":[9,30],"between":[10],"human":[11,28],"and":[12,31,85],"machines.":[13],"Applications":[14],"of":[15,72,89,113],"emotion":[16,60],"in":[18,23,47,104,111],"speech":[19],"can":[20],"be":[21],"found":[22],"several":[24],"areas":[25],"such":[26],"as":[27,98],"computer":[29],"call":[32],"centres.":[33],"In":[34,50],"recent":[35],"years,":[36],"Deep":[37],"Neural":[38,75],"Networks":[39],"(DNN)":[40],"have":[41],"been":[42],"used":[43],"with":[44],"great":[45],"success":[46],"recognizing":[48],"emotions.":[49],"this":[51],"paper,":[52],"we":[53],"present":[54],"a":[55,73,91],"new":[56],"model":[57,108],"for":[58,120],"continuous":[59],"from":[62,81],"speech.":[63],"Our":[64,107],"model,":[65],"which":[66,78],"was":[67],"trained":[68],"end-to-end,":[69],"comprised":[71],"Convolutional":[74],"Network":[76],"(CNN),":[77],"extracts":[79],"features":[80],"raw":[83],"signal,":[84],"stacked":[86],"on":[87],"top":[88],"it":[90],"2-layer":[92],"Long":[93],"Short-Term":[94],"Memory":[95],"(LSTM),":[96],"so":[97],"to":[99],"consider":[100],"contextual":[102],"information":[103],"data.":[106],"significantly":[109],"outperforms,":[110],"terms":[112],"concordance":[114],"correlation":[115],"coefficient,":[116],"state-of-the-art":[118],"methods":[119],"RECOLA":[122],"database.":[123]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":23},{"year":2024,"cited_by_count":28},{"year":2023,"cited_by_count":43},{"year":2022,"cited_by_count":57},{"year":2021,"cited_by_count":50},{"year":2020,"cited_by_count":41},{"year":2019,"cited_by_count":21},{"year":2018,"cited_by_count":2}],"updated_date":"2026-05-24T08:33:08.758527","created_date":"2025-10-10T00:00:00"}