{"id":"https://openalex.org/W4408354325","doi":"https://doi.org/10.1109/icassp49660.2025.10890265","title":"Temporal-Frequency State Space Duality: An Efficient Paradigm for Speech Emotion Recognition","display_name":"Temporal-Frequency State Space Duality: An Efficient Paradigm for Speech Emotion Recognition","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354325","doi":"https://doi.org/10.1109/icassp49660.2025.10890265"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890265","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890265","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5024790598","display_name":"Jiaqi Zhao","orcid":"https://orcid.org/0000-0003-0112-952X"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaqi Zhao","raw_affiliation_strings":["Anhui University,School of Artificial Intelligence,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Anhui University,School of Artificial Intelligence,Hefei,China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100455936","display_name":"Fei Wang","orcid":"https://orcid.org/0000-0003-1669-8338"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fei Wang","raw_affiliation_strings":["Institute of Artificial Intelligence,Hefei Comprehensive National Science Center,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence,Hefei Comprehensive National Science Center,Hefei,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100377522","display_name":"Kun Li","orcid":"https://orcid.org/0000-0001-9399-9498"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Li","raw_affiliation_strings":["Zhejiang University,CCAI,Hangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,CCAI,Hangzhou,China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003728286","display_name":"Yanyan Wei","orcid":"https://orcid.org/0000-0001-8818-6740"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanyan Wei","raw_affiliation_strings":["Hefei University of Technology,School of Computer Science and Information Engineering,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hefei University of Technology,School of Computer Science and Information Engineering,Hefei,China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076104260","display_name":"Shengeng Tang","orcid":"https://orcid.org/0000-0001-6313-2543"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengeng Tang","raw_affiliation_strings":["Hefei University of Technology,School of Computer Science and Information Engineering,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hefei University of Technology,School of Computer Science and Information Engineering,Hefei,China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100661274","display_name":"Shu Zhao","orcid":"https://orcid.org/0000-0001-7647-3603"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shu Zhao","raw_affiliation_strings":["Anhui University,School of Computer Science and Technology,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Anhui University,School of Computer Science and Technology,Hefei,China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100932834","display_name":"Xiao Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiao Sun","raw_affiliation_strings":["Institute of Artificial Intelligence,Hefei Comprehensive National Science Center,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence,Hefei Comprehensive National Science Center,Hefei,China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T10860","display_name":"Speech and Audio Processing","score":0.9556000232696533,"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":0.9556000232696533,"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":0.9160000085830688,"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":0.6394850015640259},{"id":"https://openalex.org/keywords/duality","display_name":"Duality (order theory)","score":0.5664319396018982},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5380657911300659},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5104435682296753},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5042356252670288},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.4941695034503937},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.4174514412879944},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35420727729797363},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15355908870697021},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.14608755707740784},{"id":"https://openalex.org/keywords/pure-mathematics","display_name":"Pure mathematics","score":0.08715668320655823}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6394850015640259},{"id":"https://openalex.org/C2778023678","wikidata":"https://www.wikidata.org/wiki/Q554403","display_name":"Duality (order theory)","level":2,"score":0.5664319396018982},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5380657911300659},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5104435682296753},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5042356252670288},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.4941695034503937},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.4174514412879944},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35420727729797363},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15355908870697021},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.14608755707740784},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.08715668320655823},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890265","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890265","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W2146334809","https://openalex.org/W2963686995","https://openalex.org/W3011176162","https://openalex.org/W3127806559","https://openalex.org/W3158248812","https://openalex.org/W3176201273","https://openalex.org/W3204447181","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4221162872","https://openalex.org/W4221162874","https://openalex.org/W4309660795","https://openalex.org/W4313887688","https://openalex.org/W4372266717","https://openalex.org/W4372341110","https://openalex.org/W4375869114","https://openalex.org/W4382450087","https://openalex.org/W4385823394","https://openalex.org/W4385964683","https://openalex.org/W4386424265","https://openalex.org/W4388189239","https://openalex.org/W4392903514","https://openalex.org/W4393148371","https://openalex.org/W4396612946","https://openalex.org/W4399747822","https://openalex.org/W4402727061","https://openalex.org/W4403386295","https://openalex.org/W4403791418","https://openalex.org/W4403791986","https://openalex.org/W4409367415","https://openalex.org/W6780218876","https://openalex.org/W6797578546","https://openalex.org/W6847363464","https://openalex.org/W6859298233","https://openalex.org/W6868789466","https://openalex.org/W6870290159","https://openalex.org/W6873649989"],"related_works":["https://openalex.org/W2593555778","https://openalex.org/W4253372294","https://openalex.org/W88297779","https://openalex.org/W2026789159","https://openalex.org/W2384039353","https://openalex.org/W2165483356","https://openalex.org/W2160662427","https://openalex.org/W183833198","https://openalex.org/W3126677997","https://openalex.org/W1610857240"],"abstract_inverted_index":{"Speech":[0],"Emotion":[1],"Recognition":[2],"(SER)":[3],"plays":[4],"a":[5,48,65,89,128],"critical":[6],"role":[7],"in":[8,56,120],"enhancing":[9],"user":[10],"experience":[11],"within":[12],"human-computer":[13],"interaction.":[14],"However,":[15],"existing":[16,118],"methods":[17,119],"are":[18,34],"overwhelmed":[19],"by":[20],"temporal":[21,58],"domain":[22,32],"analysis,":[23],"overlooking":[24],"the":[25,30,97,109],"valuable":[26],"envelope":[27],"structures":[28],"of":[29,122],"frequency":[31,60],"that":[33,52,115],"equally":[35],"important":[36],"for":[37,104,132],"robust":[38],"emotion":[39],"recognition.":[40],"To":[41],"overcome":[42],"this":[43],"limitation,":[44],"we":[45,63,87],"propose":[46,64],"TF-Mamba,":[47],"novel":[49],"multi-domain":[50],"framework":[51],"captures":[53],"emotional":[54,74,102],"expressions":[55],"both":[57],"and":[59,72,83,111,125],"dimensions.":[61],"Concretely,":[62],"temporal-frequency":[66],"mamba":[67],"block":[68],"to":[69,95,99],"extract":[70],"temporal-":[71],"frequency-aware":[73],"features,":[75],"achieving":[76],"an":[77],"optimal":[78],"balance":[79],"between":[80],"computational":[81],"efficiency":[82],"model":[84,98,123],"expressiveness.":[85],"Besides,":[86],"design":[88],"Complex":[90],"Metric-Distance":[91],"Triplet":[92],"(CMDT)":[93],"loss":[94],"enable":[96],"capture":[100],"representative":[101],"clues":[103],"SER.":[105],"Extensive":[106],"experiments":[107],"on":[108],"IEMOCAP":[110],"MELD":[112],"datasets":[113],"show":[114],"TF-Mamba":[116],"surpasses":[117],"terms":[121],"size":[124],"latency,":[126],"providing":[127],"more":[129],"practical":[130],"solution":[131],"future":[133],"SER":[134],"applications.":[135]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":9}],"updated_date":"2026-07-18T07:39:51.176621","created_date":"2025-10-10T00:00:00"}