{"id":"https://openalex.org/W2889507358","doi":"https://doi.org/10.21437/interspeech.2018-1477","title":"Exploring Spatio-Temporal Representations by Integrating Attention-based Bidirectional-LSTM-RNNs and FCNs for Speech Emotion Recognition","display_name":"Exploring Spatio-Temporal Representations by Integrating Attention-based Bidirectional-LSTM-RNNs and FCNs for Speech Emotion Recognition","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2889507358","doi":"https://doi.org/10.21437/interspeech.2018-1477","mag":"2889507358"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-1477","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1477","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/A5052655362","display_name":"Ziping Zhao","orcid":"https://orcid.org/0000-0002-8719-6389"},"institutions":[{"id":"https://openalex.org/I15062923","display_name":"Tianjin Normal University","ror":"https://ror.org/05x2td559","country_code":"CN","type":"education","lineage":["https://openalex.org/I15062923"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ziping Zhao","raw_affiliation_strings":["College of Computer and Information Engineering, Tianjin Normal University"],"affiliations":[{"raw_affiliation_string":"College of Computer and Information Engineering, Tianjin Normal University","institution_ids":["https://openalex.org/I15062923"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100681023","display_name":"Yu Zheng","orcid":"https://orcid.org/0000-0002-5224-4344"},"institutions":[{"id":"https://openalex.org/I15062923","display_name":"Tianjin Normal University","ror":"https://ror.org/05x2td559","country_code":"CN","type":"education","lineage":["https://openalex.org/I15062923"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Zheng","raw_affiliation_strings":["College of Computer and Information Engineering, Tianjin Normal University"],"affiliations":[{"raw_affiliation_string":"College of Computer and Information Engineering, Tianjin Normal University","institution_ids":["https://openalex.org/I15062923"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036056631","display_name":"Zixing Zhang","orcid":null},"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":"Zixing Zhang","raw_affiliation_strings":["Group on Language, Audio & Music, Imperial College London, UK"],"affiliations":[{"raw_affiliation_string":"Group on Language, Audio & Music, Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047118636","display_name":"Haishuai Wang","orcid":"https://orcid.org/0000-0003-1617-0920"},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haishuai Wang","raw_affiliation_strings":["Department of Biomedical Informatics, Harvard University"],"affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics, Harvard University","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038176352","display_name":"Yiqin Zhao","orcid":"https://orcid.org/0000-0003-1044-4732"},"institutions":[{"id":"https://openalex.org/I15062923","display_name":"Tianjin Normal University","ror":"https://ror.org/05x2td559","country_code":"CN","type":"education","lineage":["https://openalex.org/I15062923"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiqin Zhao","raw_affiliation_strings":["College of Computer and Information Engineering, Tianjin Normal University"],"affiliations":[{"raw_affiliation_string":"College of Computer and Information Engineering, Tianjin Normal University","institution_ids":["https://openalex.org/I15062923"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100323277","display_name":"Chao Li","orcid":"https://orcid.org/0000-0003-3114-2776"},"institutions":[{"id":"https://openalex.org/I15062923","display_name":"Tianjin Normal University","ror":"https://ror.org/05x2td559","country_code":"CN","type":"education","lineage":["https://openalex.org/I15062923"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Li","raw_affiliation_strings":["College of Computer and Information Engineering, Tianjin Normal University"],"affiliations":[{"raw_affiliation_string":"College of Computer and Information Engineering, Tianjin Normal University","institution_ids":["https://openalex.org/I15062923"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5052655362"],"corresponding_institution_ids":["https://openalex.org/I15062923"],"apc_list":null,"apc_paid":null,"fwci":12.9271,"has_fulltext":false,"cited_by_count":97,"citation_normalized_percentile":{"value":0.98928336,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"272","last_page":"276"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9994000196456909,"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":0.9994000196456909,"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/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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9955000281333923,"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":0.8250502347946167},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.7526176571846008},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.7111114859580994},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6539707779884338},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5998926162719727},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5516808032989502},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5492496490478516},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5240909457206726},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5106266140937805},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.44396108388900757},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.44030192494392395},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4023127853870392}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8250502347946167},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.7526176571846008},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.7111114859580994},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6539707779884338},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5998926162719727},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5516808032989502},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5492496490478516},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5240909457206726},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5106266140937805},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.44396108388900757},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.44030192494392395},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4023127853870392},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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":2,"locations":[{"id":"doi:10.21437/interspeech.2018-1477","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1477","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"},{"id":"pmh:oai:digitalcommons.fairfield.edu:engineering-facultypubs-1182","is_oa":false,"landing_page_url":"https://digitalcommons.fairfield.edu/engineering-facultypubs/181","pdf_url":null,"source":{"id":"https://openalex.org/S4377196468","display_name":"DigitalCommons - Fairfield (Fairfield University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I126350171","host_organization_name":"Fairfield University","host_organization_lineage":["https://openalex.org/I126350171"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Engineering Faculty Publications","raw_type":"conference"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2702356746","display_name":null,"funder_award_id":"61702","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5760752404","display_name":null,"funder_award_id":"Projects","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5854786607","display_name":null,"funder_award_id":"Tianjin","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6578966771","display_name":null,"funder_award_id":"61702370","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320326873","display_name":"National Laboratory of Pattern Recognition","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1600744878","https://openalex.org/W1836465849","https://openalex.org/W1869752048","https://openalex.org/W1903029394","https://openalex.org/W1987048275","https://openalex.org/W2055332436","https://openalex.org/W2074788634","https://openalex.org/W2087618018","https://openalex.org/W2095705004","https://openalex.org/W2099767163","https://openalex.org/W2133564696","https://openalex.org/W2146334809","https://openalex.org/W2295001676","https://openalex.org/W2295300449","https://openalex.org/W2398826216","https://openalex.org/W2399733683","https://openalex.org/W2408520939","https://openalex.org/W2510170536","https://openalex.org/W2512885694","https://openalex.org/W2515667479","https://openalex.org/W2551393996","https://openalex.org/W2578895956","https://openalex.org/W2611029437","https://openalex.org/W2613375858","https://openalex.org/W2616180702","https://openalex.org/W2625297138","https://openalex.org/W2750666523","https://openalex.org/W2754051771","https://openalex.org/W2800167607","https://openalex.org/W2894458059","https://openalex.org/W2962736520","https://openalex.org/W2963069010","https://openalex.org/W2963212833","https://openalex.org/W2963467407","https://openalex.org/W2963568027","https://openalex.org/W2964308564","https://openalex.org/W4308909683"],"related_works":["https://openalex.org/W4225394202","https://openalex.org/W4298287631","https://openalex.org/W2953061907","https://openalex.org/W4226493464","https://openalex.org/W4312417841","https://openalex.org/W3133861977","https://openalex.org/W3008584592","https://openalex.org/W2951211570","https://openalex.org/W3103566983","https://openalex.org/W3029198973"],"abstract_inverted_index":{"Automatic":[0],"emotion":[1,32,51,153],"recognition":[2,33,52,154],"from":[3,75],"speech,":[4],"which":[5],"is":[6,54],"an":[7],"important":[8],"and":[9,132],"challenging":[10],"task":[11],"in":[12,91],"the":[13,21,24,38,68,96,118,125,133],"field":[14],"of":[15,23,40,70,100],"affective":[16],"computing,":[17],"heavily":[18],"relies":[19],"on":[20,37,124],"effectiveness":[22],"speech":[25,50,76,101],"features":[26,106],"for":[27,49],"classification.":[28],"Previous":[29],"approaches":[30],"to":[31,45,66,93,116],"have":[34],"mostly":[35],"focused":[36],"extraction":[39,74],"carefully":[41],"hand-crafted":[42],"features.":[43],"How":[44],"model":[46],"spatio-temporal":[47,98],"dynamics":[48],"effectively":[53],"still":[55],"under":[56],"active":[57],"investigation.":[58],"In":[59],"this":[60],"paper,":[61],"we":[62],"propose":[63],"a":[64,111],"method":[65,144],"tackle":[67],"problem":[69],"emotional":[71],"relevant":[72],"feature":[73],"by":[77],"leveraging":[78],"Attention-based":[79],"Bidirectional":[80],"Long":[81],"Short-Term":[82],"Memory":[83],"Recurrent":[84],"Neural":[85],"Networks":[86],"with":[87,150],"fully":[88],"convolutional":[89],"networks":[90],"order":[92],"automatically":[94],"learn":[95],"best":[97],"representations":[99],"signals.":[102],"The":[103,121],"learned":[104],"high-level":[105],"are":[107],"then":[108],"fed":[109],"into":[110],"deep":[112],"neural":[113],"network":[114],"(DNN)":[115],"predict":[117],"final":[119],"emotion.":[120],"experimental":[122],"results":[123],"Chinese":[126],"Natural":[127],"Audio-Visual":[128],"Emotion":[129],"Database":[130],"(CHEAVD)":[131],"Interactive":[134],"Emotional":[135],"Dyadic":[136],"Motion":[137],"Capture":[138],"(IEMOCAP)":[139],"corpora":[140],"show":[141],"that":[142],"our":[143],"provides":[145],"more":[146],"accurate":[147],"predictions":[148],"compared":[149],"other":[151],"existing":[152],"algorithms.":[155]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":31},{"year":2020,"cited_by_count":17},{"year":2019,"cited_by_count":11}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}