{"id":"https://openalex.org/W2885005742","doi":"https://doi.org/10.1109/lsp.2018.2860246","title":"3-D Convolutional Recurrent Neural Networks With Attention Model for Speech Emotion Recognition","display_name":"3-D Convolutional Recurrent Neural Networks With Attention Model for Speech Emotion Recognition","publication_year":2018,"publication_date":"2018-07-26","ids":{"openalex":"https://openalex.org/W2885005742","doi":"https://doi.org/10.1109/lsp.2018.2860246","mag":"2885005742"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2018.2860246","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2018.2860246","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-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/A5101945678","display_name":"Mingyi Chen","orcid":"https://orcid.org/0000-0002-7954-9682"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Mingyi Chen","raw_affiliation_strings":["School of Information Science and Engineering, Central South University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-7954-9682","affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102718676","display_name":"Xuanji He","orcid":"https://orcid.org/0000-0003-0137-180X"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuanji He","raw_affiliation_strings":["School of Information Science and Engineering, Central South University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0003-0137-180X","affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101922033","display_name":"Jing Yang","orcid":"https://orcid.org/0000-0002-7296-8198"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Yang","raw_affiliation_strings":["School of Information Science and Engineering, Central South University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-7296-8198","affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"last","author":{"id":null,"display_name":"Han Zhang","orcid":"https://orcid.org/0000-0002-8445-5541"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Zhang","raw_affiliation_strings":["School of Information Science and Engineering, Central South University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-8445-5541","affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101945678"],"corresponding_institution_ids":["https://openalex.org/I139660479"],"apc_list":null,"apc_paid":null,"fwci":41.8238,"has_fulltext":false,"cited_by_count":503,"citation_normalized_percentile":{"value":0.99901525,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"25","issue":"10","first_page":"1440","last_page":"1444"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9962000250816345,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9930999875068665,"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/discriminative-model","display_name":"Discriminative model","score":0.726529598236084},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7190124988555908},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6543360352516174},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6174045205116272},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.603839635848999},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.5596632957458496},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.5595401525497437},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5331268906593323},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5261221528053284},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5197479724884033},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4917445480823517},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.49157652258872986},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37353408336639404},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.36144447326660156},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.16138100624084473},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.15978339314460754}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.726529598236084},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7190124988555908},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6543360352516174},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6174045205116272},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.603839635848999},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5596632957458496},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.5595401525497437},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5331268906593323},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5261221528053284},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5197479724884033},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4917445480823517},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.49157652258872986},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37353408336639404},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.36144447326660156},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.16138100624084473},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.15978339314460754},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2018.2860246","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2018.2860246","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7400000095367432}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W175750906","https://openalex.org/W854541894","https://openalex.org/W1522301498","https://openalex.org/W1554982972","https://openalex.org/W1566256432","https://openalex.org/W2047337856","https://openalex.org/W2087618018","https://openalex.org/W2133564696","https://openalex.org/W2146334809","https://openalex.org/W2158061940","https://openalex.org/W2167854178","https://openalex.org/W2271840356","https://openalex.org/W2280236323","https://openalex.org/W2294139527","https://openalex.org/W2295001676","https://openalex.org/W2399733683","https://openalex.org/W2408520939","https://openalex.org/W2470673105","https://openalex.org/W2512885694","https://openalex.org/W2620836355","https://openalex.org/W2625297138","https://openalex.org/W2750666523","https://openalex.org/W2766272105","https://openalex.org/W2962736520","https://openalex.org/W2963467407","https://openalex.org/W6631190155","https://openalex.org/W6684678644","https://openalex.org/W6697221640","https://openalex.org/W6697498398","https://openalex.org/W6714031499"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2088854863","https://openalex.org/W2011227383","https://openalex.org/W2065606036","https://openalex.org/W1976719989","https://openalex.org/W2942893872","https://openalex.org/W2184242386","https://openalex.org/W1923358586","https://openalex.org/W2735297260"],"abstract_inverted_index":{"Speech":[0],"emotion":[1],"recognition":[2],"(SER)":[3],"is":[4],"a":[5,115],"difficult":[6],"task":[7],"due":[8],"to":[9,36,79,122],"the":[10,21,28,42,55,65,72,88,129,146,149,154],"complexity":[11],"of":[12,23,74,148,159],"emotions.":[13],"The":[14],"SER":[15,84],"performances":[16,101],"are":[17,34,135],"heavily":[18],"dependent":[19],"on":[20,140],"effectiveness":[22,147],"emotional":[24,32,67],"features":[25,33,61,125],"extracted":[26],"from":[27,87],"speech.":[29],"However,":[30],"most":[31],"sensitive":[35],"emotionally":[37,75,92],"irrelevant":[38,76,93],"factors,":[39,77],"such":[40],"as":[41,137],"speaker,":[43],"speaking":[44],"styles,":[45],"and":[46,57,91,133,142,152],"environment.":[47],"In":[48,82],"this":[49],"letter,":[50],"we":[51,113],"assume":[52],"that":[53],"calculating":[54],"deltas":[56,132],"delta-deltas":[58,134],"for":[59,107,126],"personalized":[60],"not":[62],"only":[63],"preserves":[64],"effective":[66],"information":[68],"but":[69],"also":[70],"reduces":[71],"influence":[73],"leading":[78],"reduce":[80],"misclassification.":[81],"addition,":[83],"often":[85],"suffers":[86],"silent":[89],"frames":[90],"frames.":[94],"Meanwhile,":[95],"attention":[96],"mechanism":[97],"has":[98],"exhibited":[99],"outstanding":[100],"in":[102,157],"learning":[103],"relevant":[104],"feature":[105],"representations":[106],"specific":[108],"tasks.":[109],"Inspired":[110],"by":[111],"this,":[112],"propose":[114],"three-dimensional":[116],"attention-based":[117],"convolutional":[118],"recurrent":[119],"neural":[120],"networks":[121],"learn":[123],"discriminative":[124],"SER,":[127],"where":[128],"Mel-spectrogram":[130],"with":[131],"used":[136],"input.":[138],"Experiments":[139],"IEMOCAP":[141],"Emo-DB":[143],"corpus":[144],"demonstrate":[145],"proposed":[150],"method":[151],"achieve":[153],"state-of-the-art":[155],"performance":[156],"terms":[158],"unweighted":[160],"average":[161],"recall.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":15},{"year":2025,"cited_by_count":51},{"year":2024,"cited_by_count":70},{"year":2023,"cited_by_count":86},{"year":2022,"cited_by_count":90},{"year":2021,"cited_by_count":97},{"year":2020,"cited_by_count":61},{"year":2019,"cited_by_count":28},{"year":2018,"cited_by_count":5}],"updated_date":"2026-06-05T09:01:59.212387","created_date":"2025-10-10T00:00:00"}
