{"id":"https://openalex.org/W4391746473","doi":"https://doi.org/10.34133/icomputing.0073","title":"Temporal Shift Module with Pretrained Representations for Speech Emotion Recognition","display_name":"Temporal Shift Module with Pretrained Representations for Speech Emotion Recognition","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4391746473","doi":"https://doi.org/10.34133/icomputing.0073"},"language":"en","primary_location":{"id":"doi:10.34133/icomputing.0073","is_oa":true,"landing_page_url":"https://doi.org/10.34133/icomputing.0073","pdf_url":null,"source":{"id":"https://openalex.org/S4387281904","display_name":"Intelligent Computing","issn_l":"2771-5892","issn":["2771-5892"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Intelligent Computing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.34133/icomputing.0073","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101980691","display_name":"Siyuan Shen","orcid":"https://orcid.org/0000-0001-9732-9600"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siyuan Shen","raw_affiliation_strings":["Institute of AI for Education, \rEast China Normal University, Shanghai, China","School of Computer Science and Technology, \rEast China Normal University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of AI for Education, \rEast China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]},{"raw_affiliation_string":"School of Computer Science and Technology, \rEast China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085891781","display_name":"Feng Liu","orcid":"https://orcid.org/0000-0002-5289-5761"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Liu","raw_affiliation_strings":["Institute of AI for Education, \rEast China Normal University, Shanghai, China","School of Computer Science and Technology, \rEast China Normal University, Shanghai, China","East China Normal University, School of Computer Science and Technology, 1st Floor, Physics Building, No. 3663 Zhongshan North Road, Putuo District, Shan, shanghai, shanghai, 200062, East China Normal University, CHINA"],"raw_orcid":"https://orcid.org/0000-0002-5289-5761","affiliations":[{"raw_affiliation_string":"Institute of AI for Education, \rEast China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]},{"raw_affiliation_string":"School of Computer Science and Technology, \rEast China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]},{"raw_affiliation_string":"East China Normal University, School of Computer Science and Technology, 1st Floor, Physics Building, No. 3663 Zhongshan North Road, Putuo District, Shan, shanghai, shanghai, 200062, East China Normal University, CHINA","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051945922","display_name":"Hanyang Wang","orcid":"https://orcid.org/0000-0002-8171-6398"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanyang Wang","raw_affiliation_strings":["Institute of AI for Education, \rEast China Normal University, Shanghai, China","School of Computer Science and Technology, \rEast China Normal University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of AI for Education, \rEast China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]},{"raw_affiliation_string":"School of Computer Science and Technology, \rEast China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100398969","display_name":"Yunlong Wang","orcid":"https://orcid.org/0000-0002-3535-308X"},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunlong Wang","raw_affiliation_strings":["Institute of Acoustics, \rUniversity of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Acoustics, \rUniversity of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210099069"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050248676","display_name":"Aimin Zhou","orcid":"https://orcid.org/0000-0002-4768-5946"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Aimin Zhou","raw_affiliation_strings":["Institute of AI for Education, \rEast China Normal University, Shanghai, China","School of Computer Science and Technology, \rEast China Normal University, Shanghai, China","CHINA"],"raw_orcid":"https://orcid.org/0000-0002-4768-5946","affiliations":[{"raw_affiliation_string":"Institute of AI for Education, \rEast China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]},{"raw_affiliation_string":"School of Computer Science and Technology, \rEast China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]},{"raw_affiliation_string":"CHINA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.5339,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.89835013,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"3","issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998000264167786,"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"}},{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9994999766349792,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6204909086227417},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.598086416721344},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4678066074848175},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39494115114212036},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.35168343782424927},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.3501279652118683}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6204909086227417},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.598086416721344},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4678066074848175},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39494115114212036},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.35168343782424927},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.3501279652118683}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.34133/icomputing.0073","is_oa":true,"landing_page_url":"https://doi.org/10.34133/icomputing.0073","pdf_url":null,"source":{"id":"https://openalex.org/S4387281904","display_name":"Intelligent Computing","issn_l":"2771-5892","issn":["2771-5892"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Intelligent Computing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:1f24ead8edc745e0ba78d54a62133c1f","is_oa":true,"landing_page_url":"https://doaj.org/article/1f24ead8edc745e0ba78d54a62133c1f","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Intelligent Computing, Vol 3 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.34133/icomputing.0073","is_oa":true,"landing_page_url":"https://doi.org/10.34133/icomputing.0073","pdf_url":null,"source":{"id":"https://openalex.org/S4387281904","display_name":"Intelligent Computing","issn_l":"2771-5892","issn":["2771-5892"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Intelligent Computing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8945255070","display_name":null,"funder_award_id":"22511105901","funder_id":"https://openalex.org/F4320330747","funder_display_name":"Science and Technology Commission of Fengxian District, Shanghai Municipality"}],"funders":[{"id":"https://openalex.org/F4320330747","display_name":"Science and Technology Commission of Fengxian District, Shanghai Municipality","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":83,"referenced_works":["https://openalex.org/W175750906","https://openalex.org/W2033875152","https://openalex.org/W2064675550","https://openalex.org/W2087618018","https://openalex.org/W2112796928","https://openalex.org/W2117671523","https://openalex.org/W2127141656","https://openalex.org/W2143612262","https://openalex.org/W2146334809","https://openalex.org/W2163922914","https://openalex.org/W2181741066","https://openalex.org/W2194775991","https://openalex.org/W2239141610","https://openalex.org/W2399733683","https://openalex.org/W2473930607","https://openalex.org/W2526050071","https://openalex.org/W2531409750","https://openalex.org/W2625297138","https://openalex.org/W2752782242","https://openalex.org/W2766272105","https://openalex.org/W2766736793","https://openalex.org/W2803193013","https://openalex.org/W2889717020","https://openalex.org/W2896457183","https://openalex.org/W2903739847","https://openalex.org/W2935542736","https://openalex.org/W2936774411","https://openalex.org/W2963163009","https://openalex.org/W2963844898","https://openalex.org/W2964110616","https://openalex.org/W2964199361","https://openalex.org/W2970583420","https://openalex.org/W2972602947","https://openalex.org/W2973157397","https://openalex.org/W2990152177","https://openalex.org/W2997399314","https://openalex.org/W3015213852","https://openalex.org/W3015537910","https://openalex.org/W3021469861","https://openalex.org/W3024869864","https://openalex.org/W3025165719","https://openalex.org/W3036601975","https://openalex.org/W3049430014","https://openalex.org/W3095173472","https://openalex.org/W3097777922","https://openalex.org/W3122100772","https://openalex.org/W3144073776","https://openalex.org/W3157506437","https://openalex.org/W3157923770","https://openalex.org/W3162993161","https://openalex.org/W3163142165","https://openalex.org/W3167533889","https://openalex.org/W3169320628","https://openalex.org/W3183804933","https://openalex.org/W3197156295","https://openalex.org/W3197580070","https://openalex.org/W3197642003","https://openalex.org/W3199964822","https://openalex.org/W3208480086","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4221140371","https://openalex.org/W4221162793","https://openalex.org/W4221162872","https://openalex.org/W4224918181","https://openalex.org/W4225320271","https://openalex.org/W4226028923","https://openalex.org/W4226334005","https://openalex.org/W4280542824","https://openalex.org/W4281492411","https://openalex.org/W4286544676","https://openalex.org/W4293370939","https://openalex.org/W4297727296","https://openalex.org/W4297775537","https://openalex.org/W4297808394","https://openalex.org/W4312443924","https://openalex.org/W4312820606","https://openalex.org/W4372341110","https://openalex.org/W4375869379","https://openalex.org/W4386065595","https://openalex.org/W4394666973","https://openalex.org/W6607193717","https://openalex.org/W6795140394"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2931662336","https://openalex.org/W2077865380","https://openalex.org/W4401768695","https://openalex.org/W2765597752","https://openalex.org/W2134894512","https://openalex.org/W2083375246","https://openalex.org/W3126677997","https://openalex.org/W1610857240"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,12,130,160],"self-supervised":[3],"models":[4,117],"have":[5],"led":[6],"to":[7,60,104],"effective":[8],"pretrained":[9,26,38,58],"speech":[10,14],"representations":[11,27,59],"downstream":[13,46,161,177],"emotion":[15],"recognition":[16],"tasks.":[17],"However,":[18],"previous":[19],"research":[20],"has":[21],"primarily":[22],"focused":[23],"on":[24,34,121],"exploiting":[25],"by":[28],"simply":[29],"adding":[30],"a":[31,53],"linear":[32],"head":[33],"top":[35],"of":[36,44,102,114,155,173],"the":[37,42,45,75,106,122,153,156],"model,":[39],"while":[40],"overlooking":[41],"design":[43],"network.":[47],"In":[48,135],"this":[49],"paper,":[50],"we":[51,79,94,151],"propose":[52,95],"temporal":[54,76,115,157],"shift":[55,77,82,116,158,175],"module":[56,159],"with":[57],"integrate":[61],"channel-wise":[62,174],"information":[63],"without":[64],"introducing":[65],"additional":[66],"parameters":[67],"or":[68],"floating-point":[69],"operations":[70],"per":[71],"second.":[72],"By":[73],"incorporating":[74],"module,":[78],"developed":[80],"corresponding":[81],"variants":[83],"for":[84,170],"3":[85],"baseline":[86],"building":[87],"blocks:":[88],"ShiftCNN,":[89],"ShiftLSTM,":[90],"and":[91,100,110,132,143,176],"Shiftformer.":[92],"Furthermore,":[93],"2":[96],"technical":[97],"strategies,":[98],"placement":[99],"proportion":[101],"shift,":[103],"balance":[105],"trade-off":[107],"between":[108],"mingling":[109],"misalignment.":[111],"Our":[112],"family":[113],"outperforms":[118],"state-of-the-art":[119],"methods":[120],"benchmark":[123],"Interactive":[124],"Emotional":[125],"Dyadic":[126],"Motion":[127],"Capture":[128],"dataset":[129],"fine-tuning":[131],"feature-extraction":[133],"scenarios.":[134],"addition,":[136],"through":[137],"comprehensive":[138],"experiments":[139],"using":[140],"wav2vec":[141],"2.0":[142],"Hidden-Unit":[144],"Bidirectional":[145],"Encoder":[146],"Representations":[147],"from":[148],"Transformers":[149],"representations,":[150],"identified":[152],"behavior":[154],"models,":[162],"which":[163],"may":[164],"serve":[165],"as":[166],"an":[167],"empirical":[168],"guideline":[169],"future":[171],"exploration":[172],"network":[178],"design.":[179]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}