{"id":"https://openalex.org/W2898436987","doi":"https://doi.org/10.1145/3274783.3275184","title":"Speech Emotion Recognition via Attention-based DNN from Multi-Task Learning","display_name":"Speech Emotion Recognition via Attention-based DNN from Multi-Task Learning","publication_year":2018,"publication_date":"2018-10-26","ids":{"openalex":"https://openalex.org/W2898436987","doi":"https://doi.org/10.1145/3274783.3275184","mag":"2898436987"},"language":"en","primary_location":{"id":"doi:10.1145/3274783.3275184","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3274783.3275184","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM Conference on Embedded Networked Sensor Systems","raw_type":"proceedings-article"},"type":"conference-paper","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/A5069637938","display_name":"Fei Ma","orcid":"https://orcid.org/0000-0003-4906-6142"},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Ma","raw_affiliation_strings":["Tsinghua-Berkeley Shenzhen Institute, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua-Berkeley Shenzhen Institute, Tsinghua University","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103049399","display_name":"Weixi Gu","orcid":"https://orcid.org/0000-0002-9759-601X"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weixi Gu","raw_affiliation_strings":["University of California, Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100441703","display_name":"Wei Zhang","orcid":"https://orcid.org/0000-0002-8208-3342"},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Zhang","raw_affiliation_strings":["Tsinghua-Berkeley Shenzhen Institute, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua-Berkeley Shenzhen Institute, Tsinghua University","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019716362","display_name":"Shiguang Ni","orcid":"https://orcid.org/0000-0002-4303-7386"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiguang Ni","raw_affiliation_strings":["Graduate School at Shenzhen, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School at Shenzhen, Tsinghua University","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088293566","display_name":"Shao\u2010Lun Huang","orcid":"https://orcid.org/0000-0003-2827-4022"},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shao-Lun Huang","raw_affiliation_strings":["Tsinghua-Berkeley Shenzhen Institute, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua-Berkeley Shenzhen Institute, Tsinghua University","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100351850","display_name":"Lin Zhang","orcid":"https://orcid.org/0000-0002-4394-2685"},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Zhang","raw_affiliation_strings":["Tsinghua-Berkeley Shenzhen Institute, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua-Berkeley Shenzhen Institute, Tsinghua University","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"363","last_page":"364"},"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":0.9986000061035156,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9948999881744385,"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/sadness","display_name":"Sadness","score":0.8183190822601318},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7246866822242737},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6780615448951721},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.6345019340515137},{"id":"https://openalex.org/keywords/happiness","display_name":"Happiness","score":0.6022205948829651},{"id":"https://openalex.org/keywords/anger","display_name":"Anger","score":0.5988082885742188},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5467627048492432},{"id":"https://openalex.org/keywords/emotion-classification","display_name":"Emotion classification","score":0.5253793001174927},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43775543570518494},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.420889675617218},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.12305828928947449}],"concepts":[{"id":"https://openalex.org/C2779812673","wikidata":"https://www.wikidata.org/wiki/Q169251","display_name":"Sadness","level":3,"score":0.8183190822601318},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7246866822242737},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6780615448951721},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.6345019340515137},{"id":"https://openalex.org/C2778999518","wikidata":"https://www.wikidata.org/wiki/Q8","display_name":"Happiness","level":2,"score":0.6022205948829651},{"id":"https://openalex.org/C2779302386","wikidata":"https://www.wikidata.org/wiki/Q79871","display_name":"Anger","level":2,"score":0.5988082885742188},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5467627048492432},{"id":"https://openalex.org/C206310091","wikidata":"https://www.wikidata.org/wiki/Q750859","display_name":"Emotion classification","level":2,"score":0.5253793001174927},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43775543570518494},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.420889675617218},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.12305828928947449},{"id":"https://openalex.org/C118552586","wikidata":"https://www.wikidata.org/wiki/Q7867","display_name":"Psychiatry","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3274783.3275184","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3274783.3275184","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM Conference on Embedded Networked Sensor Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2074788634","https://openalex.org/W2125462608","https://openalex.org/W2192412620","https://openalex.org/W2343758848","https://openalex.org/W2606176798","https://openalex.org/W2626821150","https://openalex.org/W2753992645","https://openalex.org/W2778073151","https://openalex.org/W2799604656"],"related_works":["https://openalex.org/W4365519294","https://openalex.org/W3031187173","https://openalex.org/W3135436127","https://openalex.org/W2805647211","https://openalex.org/W2100930849","https://openalex.org/W2557139663","https://openalex.org/W2073249509","https://openalex.org/W2481378124","https://openalex.org/W1980267738","https://openalex.org/W3179181153"],"abstract_inverted_index":{"Speech":[0],"unlocks":[1],"the":[2,33,37,72,78,86,98,108],"huge":[3],"potentials":[4],"in":[5,26,85,113],"emotion":[6,15,29,38,73,99,111],"recognition.":[7,39,100],"High":[8],"accurate":[9],"and":[10,59,81],"real-time":[11,109],"understanding":[12],"of":[13,51],"human":[14],"via":[16],"speech":[17],"assists":[18],"Human-Computer":[19],"Interaction.":[20],"Previous":[21],"works":[22],"are":[23],"often":[24],"limited":[25],"either":[27],"coarse-grained":[28],"learning":[30],"tasks":[31],"or":[32],"low":[34],"precisions":[35],"on":[36,71,97,107],"To":[40],"solve":[41],"these":[42],"problems,":[43],"we":[44],"construct":[45],"a":[46,64],"real-world":[47],"large-scale":[48],"corpus":[49],"composed":[50],"4":[52],"common":[53],"emotions":[54],"(i.e.,":[55,69],"anger,":[56],"happiness,":[57],"neutral":[58],"sadness).":[60],"We":[61],"also":[62],"propose":[63],"multi-task":[65],"attention-based":[66],"DNN":[67],"model":[68],"MT-A-DNN)":[70],"learning.":[74],"MT-A-DNN":[75,93],"efficiently":[76],"learns":[77],"high-order":[79],"dependency":[80],"non-linear":[82],"correlations":[83],"underlying":[84],"audio":[87],"data.":[88],"Extensive":[89],"experiments":[90],"show":[91],"that":[92],"outperforms":[94],"conventional":[95],"methods":[96],"It":[101],"could":[102],"take":[103],"one":[104],"step":[105],"further":[106],"acoustic":[110],"recognition":[112],"many":[114],"smart":[115],"audio-devices.":[116]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}