{"id":"https://openalex.org/W2806051338","doi":"https://doi.org/10.23919/apsipa.2018.8659587","title":"Attention Based Fully Convolutional Network for Speech Emotion Recognition","display_name":"Attention Based Fully Convolutional Network for Speech Emotion Recognition","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2806051338","doi":"https://doi.org/10.23919/apsipa.2018.8659587","mag":"2806051338"},"language":"en","primary_location":{"id":"doi:10.23919/apsipa.2018.8659587","is_oa":false,"landing_page_url":"https://doi.org/10.23919/apsipa.2018.8659587","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1806.01506","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yuanyuan Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuanyuan Zhang","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jun Du","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Du","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zirui Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zirui Wang","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jianshu Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianshu Zhang","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":null,"display_name":"Yanhui Tu","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanhui Tu","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":8.3276,"has_fulltext":false,"cited_by_count":111,"citation_normalized_percentile":{"value":0.97800323,"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":"1771","last_page":"1775"},"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":0.9980999827384949,"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":0.9976999759674072,"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/spectrogram","display_name":"Spectrogram","score":0.7800999879837036},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.5795000195503235},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5699999928474426},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.48010000586509705},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4781000018119812},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4758000075817108},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.44690001010894775},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.3912999927997589}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8004000186920166},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7800999879837036},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6539000272750854},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5795000195503235},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5699999928474426},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5529000163078308},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.48010000586509705},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4781000018119812},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4758000075817108},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.44690001010894775},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3912999927997589},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.39089998602867126},{"id":"https://openalex.org/C206310091","wikidata":"https://www.wikidata.org/wiki/Q750859","display_name":"Emotion classification","level":2,"score":0.36579999327659607},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3564999997615814},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.35429999232292175},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3440000116825104},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33239999413490295},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.287200003862381},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.28119999170303345},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2696000039577484},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.23919/apsipa.2018.8659587","is_oa":false,"landing_page_url":"https://doi.org/10.23919/apsipa.2018.8659587","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1806.01506","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1806.01506","pdf_url":"https://arxiv.org/pdf/1806.01506","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:1806.01506","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1806.01506","pdf_url":"https://arxiv.org/pdf/1806.01506","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1902237438","https://openalex.org/W1903029394","https://openalex.org/W2003948868","https://openalex.org/W2032254851","https://openalex.org/W2061068689","https://openalex.org/W2074788634","https://openalex.org/W2099767163","https://openalex.org/W2102605133","https://openalex.org/W2117539524","https://openalex.org/W2146334809","https://openalex.org/W2194775991","https://openalex.org/W2214134199","https://openalex.org/W2399733683","https://openalex.org/W2470673105","https://openalex.org/W2587277634","https://openalex.org/W2623860192","https://openalex.org/W2625297138","https://openalex.org/W2648194195","https://openalex.org/W2747664154","https://openalex.org/W6608355301","https://openalex.org/W6682778277","https://openalex.org/W6684191040","https://openalex.org/W6697498398"],"related_works":[],"abstract_inverted_index":{"Speech":[0],"emotion":[1,13,27,63],"recognition":[2],"is":[3,14,19,46,72,107,116],"a":[4,37,54,153],"challenging":[5],"task":[6],"for":[7,61],"three":[8],"main":[9],"reasons:":[10],"1)":[11],"human":[12,26],"abstract,":[15],"which":[16,101],"means":[17],"it":[18,71],"hard":[20],"to":[21,74,84,119,126],"distinguish;":[22],"2)":[23],"in":[24,32],"general,":[25],"can":[28,94],"only":[29],"be":[30,98],"detected":[31],"some":[33],"specific":[34],"moments":[35],"during":[36],"long":[38],"utterance;":[39],"3)":[40],"speech":[41,62,105],"data":[42],"with":[43,131,152],"emotional":[44],"labeling":[45],"usually":[47],"limited.":[48],"In":[49],"this":[50],"paper,":[51],"we":[52],"present":[53],"novel":[55],"attention":[56,92],"based":[57,135],"fully":[58,67],"convolutional":[59,68],"network":[60,69],"recognition.":[64],"We":[65],"employ":[66],"as":[70],"able":[73],"handle":[75],"variable-length":[76],"speech,":[77],"free":[78],"of":[79,82,100,104,156,162],"the":[80,113,121,140,145,149],"demand":[81],"segmentation":[83],"keep":[85],"critical":[86],"information":[87],"not":[88],"lost.":[89],"The":[90],"proposed":[91,146],"mechanism":[93],"make":[95],"our":[96],"model":[97,147],"aware":[99],"time-frequency":[102],"region":[103],"spectrogram":[106],"more":[108],"emotion-relevant.":[109],"Considering":[110],"limited":[111],"data,":[112],"transfer":[114],"learning":[115],"also":[117],"adapted":[118],"improve":[120],"accuracy.":[122],"Especially,":[123],"it's":[124],"interesting":[125],"observe":[127],"obvious":[128],"improvement":[129],"obtained":[130],"natural":[132],"scene":[133],"image":[134],"pre-trained":[136],"model.":[137],"Validated":[138],"on":[139],"publicly":[141],"available":[142],"IEMOCAP":[143],"corpus,":[144],"outperformed":[148],"state-of-the-art":[150],"methods":[151],"weighted":[154],"accuracy":[155,161],"70.4%":[157],"and":[158],"an":[159],"unweighted":[160],"63.9%":[163],"respectively.":[164]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":22},{"year":2022,"cited_by_count":23},{"year":2021,"cited_by_count":21},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":9}],"updated_date":"2026-04-25T08:17:42.794288","created_date":"2018-06-13T00:00:00"}