{"id":"https://openalex.org/W4392902646","doi":"https://doi.org/10.1109/icassp48485.2024.10447726","title":"Speech Swin-Transformer: Exploring a Hierarchical Transformer with Shifted Windows for Speech Emotion Recognition","display_name":"Speech Swin-Transformer: Exploring a Hierarchical Transformer with Shifted Windows for Speech Emotion Recognition","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392902646","doi":"https://doi.org/10.1109/icassp48485.2024.10447726"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447726","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447726","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100424449","display_name":"Yong Wang","orcid":"https://orcid.org/0000-0002-4934-9831"},"institutions":[{"id":"https://openalex.org/I4210100356","display_name":"Ministry of Education","ror":"https://ror.org/018f7hf93","country_code":"CL","type":"government","lineage":["https://openalex.org/I4210100356"]},{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CL","CN"],"is_corresponding":false,"raw_author_name":"Yong Wang","raw_affiliation_strings":["Southeast University,Key Laboratory of Child Development and Learning Science of Ministry of Education,Nanjing,China","School of Information Science and Engineering, Southeast University, Nanjing, China","Key Laboratory of Child Development and Learning Science of Ministry of Education, Southeast University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southeast University,Key Laboratory of Child Development and Learning Science of Ministry of Education,Nanjing,China","institution_ids":["https://openalex.org/I4210100356"]},{"raw_affiliation_string":"School of Information Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]},{"raw_affiliation_string":"Key Laboratory of Child Development and Learning Science of Ministry of Education, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054796879","display_name":"Cheng Lu","orcid":"https://orcid.org/0000-0002-1477-1020"},"institutions":[{"id":"https://openalex.org/I4210100356","display_name":"Ministry of Education","ror":"https://ror.org/018f7hf93","country_code":"CL","type":"government","lineage":["https://openalex.org/I4210100356"]},{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CL","CN"],"is_corresponding":false,"raw_author_name":"Cheng Lu","raw_affiliation_strings":["Southeast University,Key Laboratory of Child Development and Learning Science of Ministry of Education,Nanjing,China","School of Biological Science and Medical Engineering, Southeast University, Nanjing, China","Key Laboratory of Child Development and Learning Science of Ministry of Education, Southeast University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southeast University,Key Laboratory of Child Development and Learning Science of Ministry of Education,Nanjing,China","institution_ids":["https://openalex.org/I4210100356"]},{"raw_affiliation_string":"School of Biological Science and Medical Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]},{"raw_affiliation_string":"Key Laboratory of Child Development and Learning Science of Ministry of Education, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091060125","display_name":"Hailun Lian","orcid":"https://orcid.org/0000-0002-1355-9503"},"institutions":[{"id":"https://openalex.org/I4210100356","display_name":"Ministry of Education","ror":"https://ror.org/018f7hf93","country_code":"CL","type":"government","lineage":["https://openalex.org/I4210100356"]},{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CL","CN"],"is_corresponding":false,"raw_author_name":"Hailun Lian","raw_affiliation_strings":["Southeast University,Key Laboratory of Child Development and Learning Science of Ministry of Education,Nanjing,China","Key Laboratory of Child Development and Learning Science of Ministry of Education, Southeast University, Nanjing, China","School of Information Science and Engineering, Southeast University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southeast University,Key Laboratory of Child Development and Learning Science of Ministry of Education,Nanjing,China","institution_ids":["https://openalex.org/I4210100356"]},{"raw_affiliation_string":"Key Laboratory of Child Development and Learning Science of Ministry of Education, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]},{"raw_affiliation_string":"School of Information Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100748465","display_name":"Zhao Yan","orcid":"https://orcid.org/0000-0002-0468-8565"},"institutions":[{"id":"https://openalex.org/I4210100356","display_name":"Ministry of Education","ror":"https://ror.org/018f7hf93","country_code":"CL","type":"government","lineage":["https://openalex.org/I4210100356"]},{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CL","CN"],"is_corresponding":false,"raw_author_name":"Yan Zhao","raw_affiliation_strings":["Southeast University,Key Laboratory of Child Development and Learning Science of Ministry of Education,Nanjing,China","School of Information Science and Engineering, Southeast University, Nanjing, China","Key Laboratory of Child Development and Learning Science of Ministry of Education, Southeast University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southeast University,Key Laboratory of Child Development and Learning Science of Ministry of Education,Nanjing,China","institution_ids":["https://openalex.org/I4210100356"]},{"raw_affiliation_string":"School of Information Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]},{"raw_affiliation_string":"Key Laboratory of Child Development and Learning Science of Ministry of Education, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043060302","display_name":"Bj\u00f6rn W. Schuller","orcid":"https://orcid.org/0000-0002-6478-8699"},"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":"Bj\u00f6rn W. Schuller","raw_affiliation_strings":["Imperial College,GLAM - the Group on Language, Audio, &amp; Music,London,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College,GLAM - the Group on Language, Audio, &amp; Music,London,UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027316177","display_name":"Yuan Zong","orcid":"https://orcid.org/0000-0002-0839-8792"},"institutions":[{"id":"https://openalex.org/I4210100356","display_name":"Ministry of Education","ror":"https://ror.org/018f7hf93","country_code":"CL","type":"government","lineage":["https://openalex.org/I4210100356"]},{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CL","CN"],"is_corresponding":false,"raw_author_name":"Yuan Zong","raw_affiliation_strings":["Southeast University,Key Laboratory of Child Development and Learning Science of Ministry of Education,Nanjing,China","Key Laboratory of Child Development and Learning Science of Ministry of Education, Southeast University, Nanjing, China","Pazhou Lab, Guangzhou, China","School of Biological Science and Medical Engineering, Southeast University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southeast University,Key Laboratory of Child Development and Learning Science of Ministry of Education,Nanjing,China","institution_ids":["https://openalex.org/I4210100356"]},{"raw_affiliation_string":"Key Laboratory of Child Development and Learning Science of Ministry of Education, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]},{"raw_affiliation_string":"Pazhou Lab, Guangzhou, China","institution_ids":[]},{"raw_affiliation_string":"School of Biological Science and Medical Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029771864","display_name":"Wenming Zheng","orcid":"https://orcid.org/0000-0002-7764-5179"},"institutions":[{"id":"https://openalex.org/I4210100356","display_name":"Ministry of Education","ror":"https://ror.org/018f7hf93","country_code":"CL","type":"government","lineage":["https://openalex.org/I4210100356"]},{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CL","CN"],"is_corresponding":false,"raw_author_name":"Wenming Zheng","raw_affiliation_strings":["Southeast University,Key Laboratory of Child Development and Learning Science of Ministry of Education,Nanjing,China","Pazhou Lab, Guangzhou, China","School of Biological Science and Medical Engineering, Southeast University, Nanjing, China","Key Laboratory of Child Development and Learning Science of Ministry of Education, Southeast University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southeast University,Key Laboratory of Child Development and Learning Science of Ministry of Education,Nanjing,China","institution_ids":["https://openalex.org/I4210100356"]},{"raw_affiliation_string":"Pazhou Lab, Guangzhou, China","institution_ids":[]},{"raw_affiliation_string":"School of Biological Science and Medical Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]},{"raw_affiliation_string":"Key Laboratory of Child Development and Learning Science of Ministry of Education, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":13.6803,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":{"value":0.99230886,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"11646","last_page":"11650"},"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":0.9993000030517578,"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":0.9970999956130981,"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":0.6757718920707703},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6397209167480469},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5934776663780212},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.4195645749568939},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.4153633415699005},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.4141841232776642},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3959954082965851},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3295133113861084},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32888320088386536},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.18227988481521606}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6757718920707703},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6397209167480469},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5934776663780212},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.4195645749568939},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.4153633415699005},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.4141841232776642},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3959954082965851},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3295133113861084},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32888320088386536},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.18227988481521606},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447726","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447726","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1448944835","display_name":null,"funder_award_id":"2023M740600","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G3114819178","display_name":null,"funder_award_id":"2023QNRC001","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5033343354","display_name":null,"funder_award_id":"61921004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7506227641","display_name":null,"funder_award_id":"U2003207","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7544658856","display_name":null,"funder_award_id":"BK20192004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8324160470","display_name":null,"funder_award_id":"2022YFC2405600","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320321605","display_name":"Government of Jiangsu Province","ror":"https://ror.org/004svx814"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2099767163","https://openalex.org/W2146334809","https://openalex.org/W2784665486","https://openalex.org/W3126625480","https://openalex.org/W3133696297","https://openalex.org/W3138516171","https://openalex.org/W3139270985","https://openalex.org/W3161659450","https://openalex.org/W4205698766","https://openalex.org/W4224234075","https://openalex.org/W4226239215","https://openalex.org/W4283791586","https://openalex.org/W4286544676","https://openalex.org/W4293363567","https://openalex.org/W4295312788","https://openalex.org/W4312857458","https://openalex.org/W4313887688","https://openalex.org/W4323569712","https://openalex.org/W4385245566","https://openalex.org/W4385822457","https://openalex.org/W4388998763","https://openalex.org/W6766978945","https://openalex.org/W6784333009","https://openalex.org/W6790690058"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W4402568167","https://openalex.org/W3179495260","https://openalex.org/W3016124757","https://openalex.org/W2897924318","https://openalex.org/W2138997758","https://openalex.org/W3034520363"],"abstract_inverted_index":{"Swin-Transformer":[0,168],"has":[1],"demonstrated":[2],"remarkable":[3],"success":[4],"in":[5,72,93],"computer":[6],"vision":[7],"by":[8,150],"leveraging":[9],"its":[10],"hierarchical":[11,43,147],"feature":[12],"representation":[13,149],"based":[14],"on":[15],"Transformer.":[16],"In":[17],"speech":[18,28,44,55,67,148],"signals,":[19],"emotional":[20,105,144],"information":[21,106],"is":[22,99],"distributed":[23],"across":[24,107],"different":[25],"scales":[26],"of":[27,77,90,110,131,155],"features,":[29],"e.":[30],"g.,":[31],"word,":[32],"phrase,":[33],"and":[34],"utterance.":[35],"Drawing":[36],"above":[37],"inspiration,":[38],"this":[39],"paper":[40],"presents":[41],"a":[42,88,95,119,137],"Transformer":[45,98,122,156],"with":[46],"shifted":[47,120],"windows":[48],"to":[49,101,123,141,159],"aggregate":[50,142],"multi-scale":[51],"emotion":[52,56],"features":[53,145],"for":[54,125,146],"recognition":[57],"(SER),":[58],"called":[59],"Speech":[60,167],"Swin-Transformer.":[61],"Specifically,":[62],"we":[63,116,135],"first":[64],"divide":[65],"the":[66,73,129,152,170],"spectrogram":[68],"into":[69],"segment-level":[70,82,143],"patches":[71,83,109],"time":[74],"domain,":[75],"composed":[76],"multiple":[78],"frame":[79,108],"patches.":[80,133],"These":[81],"are":[84],"then":[85],"encoded":[86],"using":[87],"stack":[89],"Swin":[91],"blocks,":[92],"which":[94],"local":[96,103],"window":[97,121],"utilized":[100],"explore":[102],"inter-frame":[104],"each":[111],"segment":[112,132],"patch.":[113],"After":[114],"that,":[115],"also":[117],"design":[118],"compensate":[124],"patch":[126,138],"correlations":[127],"near":[128],"boundaries":[130],"Finally,":[134],"employ":[136],"merging":[139],"operation":[140],"expanding":[151],"receptive":[153],"field":[154],"from":[157],"frame-level":[158],"segment-level.":[160],"Experimental":[161],"results":[162],"demonstrate":[163],"that":[164],"our":[165],"proposed":[166],"outperforms":[169],"state-of-the-art":[171],"methods.":[172]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":20},{"year":2024,"cited_by_count":10}],"updated_date":"2026-07-07T14:30:12.667765","created_date":"2025-10-10T00:00:00"}
