{"id":"https://openalex.org/W4372341110","doi":"https://doi.org/10.1109/icassp49357.2023.10095193","title":"Mingling or Misalignment? Temporal Shift for Speech Emotion Recognition with Pre-Trained Representations","display_name":"Mingling or Misalignment? Temporal Shift for Speech Emotion Recognition with Pre-Trained Representations","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372341110","doi":"https://doi.org/10.1109/icassp49357.2023.10095193"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095193","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095193","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/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":["East China Normal University,Shanghai Institute of AI for Education,Shanghai,China","School of Computer Science and Technology, East China Normal University, Shanghai, China","Shanghai Institute of AI for Education, East China Normal University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China Normal University,Shanghai Institute of AI for Education,Shanghai,China","institution_ids":["https://openalex.org/I66867065"]},{"raw_affiliation_string":"School of Computer Science and Technology, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]},{"raw_affiliation_string":"Shanghai Institute of AI for Education, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101774464","display_name":"Feng Liu","orcid":"https://orcid.org/0000-0002-5311-3178"},"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":["East China Normal University,Shanghai Institute of AI for Education,Shanghai,China","School of Computer Science and Technology, East China Normal University, Shanghai, China","Shanghai Institute of AI for Education, East China Normal University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China Normal University,Shanghai Institute of AI for Education,Shanghai,China","institution_ids":["https://openalex.org/I66867065"]},{"raw_affiliation_string":"School of Computer Science and Technology, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]},{"raw_affiliation_string":"Shanghai Institute of AI for Education, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"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":["East China Normal University,Shanghai Institute of AI for Education,Shanghai,China","School of Computer Science and Technology, East China Normal University, Shanghai, China","Shanghai Institute of AI for Education, East China Normal University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China Normal University,Shanghai Institute of AI for Education,Shanghai,China","institution_ids":["https://openalex.org/I66867065"]},{"raw_affiliation_string":"School of Computer Science and Technology, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]},{"raw_affiliation_string":"Shanghai Institute of AI for Education, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I66867065"],"apc_list":null,"apc_paid":null,"fwci":9.5135,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.98427132,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9997000098228455,"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":0.9994999766349792,"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/computer-science","display_name":"Computer science","score":0.7898067235946655},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6867236495018005},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5808127522468567},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5621131062507629},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5562939047813416},{"id":"https://openalex.org/keywords/paradigm-shift","display_name":"Paradigm shift","score":0.493085116147995},{"id":"https://openalex.org/keywords/time-shifting","display_name":"Time shifting","score":0.47794511914253235},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4450169503688812},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44074875116348267},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.43328022956848145},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.43305474519729614},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.4196930229663849},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4180450439453125},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2607226073741913},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07631498575210571}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7898067235946655},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6867236495018005},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5808127522468567},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5621131062507629},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5562939047813416},{"id":"https://openalex.org/C43540301","wikidata":"https://www.wikidata.org/wiki/Q689971","display_name":"Paradigm shift","level":2,"score":0.493085116147995},{"id":"https://openalex.org/C104759252","wikidata":"https://www.wikidata.org/wiki/Q187120","display_name":"Time shifting","level":3,"score":0.47794511914253235},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4450169503688812},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44074875116348267},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.43328022956848145},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.43305474519729614},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.4196930229663849},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4180450439453125},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2607226073741913},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07631498575210571},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C761482","wikidata":"https://www.wikidata.org/wiki/Q118093","display_name":"Transmission (telecommunications)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095193","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095193","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.5}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1828163288","https://openalex.org/W2064675550","https://openalex.org/W2146334809","https://openalex.org/W2541674938","https://openalex.org/W2901751978","https://openalex.org/W2990152177","https://openalex.org/W3036601975","https://openalex.org/W3162993161","https://openalex.org/W3197156295","https://openalex.org/W3197642003","https://openalex.org/W3206192140","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3216764662","https://openalex.org/W4221162793","https://openalex.org/W4221162872","https://openalex.org/W4225320271","https://openalex.org/W4297841801","https://openalex.org/W4312443924","https://openalex.org/W4312820606","https://openalex.org/W4385245566","https://openalex.org/W6638749077","https://openalex.org/W6729059855","https://openalex.org/W6739901393","https://openalex.org/W6780218876","https://openalex.org/W6802546489"],"related_works":["https://openalex.org/W2053269318","https://openalex.org/W2364370872","https://openalex.org/W4214843831","https://openalex.org/W2097963413","https://openalex.org/W4391747873","https://openalex.org/W173782983","https://openalex.org/W2470233364","https://openalex.org/W2076672350","https://openalex.org/W4402058720","https://openalex.org/W3015581276"],"abstract_inverted_index":{"Fueled":[0],"by":[1],"recent":[2],"advances":[3],"of":[4,37,44,102,106,110],"self-supervised":[5],"models,":[6],"pre-trained":[7,27,39],"speech":[8,15],"representations":[9,28],"proved":[10],"effective":[11],"for":[12],"the":[13,38,42,45,68,90,116,120],"downstream":[14,46],"emotion":[16],"recognition":[17],"(SER)":[18],"task.":[19],"Most":[20],"prior":[21],"works":[22],"mainly":[23],"focus":[24],"on":[25,35,119],"exploiting":[26],"and":[29,85,94,104,127],"just":[30],"adopt":[31],"a":[32,53],"linear":[33],"head":[34],"top":[36],"model,":[40],"neglecting":[41],"design":[43],"network.":[47],"In":[48],"this":[49],"paper,":[50],"we":[51,96],"propose":[52,97],"temporal":[54,69,111],"shift":[55,70,80,103,112],"module":[56],"to":[57,88],"mingle":[58],"channel-wise":[59],"information":[60],"without":[61],"introducing":[62],"any":[63],"parameter":[64],"or":[65],"FLOP.":[66],"With":[67],"module,":[71],"three":[72],"designed":[73],"baseline":[74],"building":[75],"blocks":[76],"evolve":[77],"into":[78],"corresponding":[79],"variants,":[81],"i.e.":[82],"ShiftCNN,":[83],"ShiftLSTM,":[84],"Shiftformer.":[86],"Moreover,":[87],"balance":[89],"trade-off":[91],"between":[92],"mingling":[93],"misalignment,":[95],"two":[98],"technical":[99],"strategies,":[100],"placement":[101],"proportion":[105],"shift.":[107],"The":[108],"family":[109],"models":[113],"all":[114],"outperforms":[115],"state-of-the-art":[117],"methods":[118],"benchmark":[121],"IEMOCAP":[122],"dataset":[123],"under":[124],"both":[125],"finetuning":[126],"feature":[128],"extraction":[129],"settings.":[130],"Our":[131],"code":[132],"is":[133],"available":[134],"at":[135],"https://github.com/ECNU-Cross-Innovation-Lab/ShiftSER.":[136]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}