{"id":"https://openalex.org/W4408353379","doi":"https://doi.org/10.1109/icassp49660.2025.10890812","title":"Metadata-Enhanced Speech Emotion Recognition: Augmented Residual Integration and Co-Attention in Two-Stage Fine-Tuning","display_name":"Metadata-Enhanced Speech Emotion Recognition: Augmented Residual Integration and Co-Attention in Two-Stage Fine-Tuning","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353379","doi":"https://doi.org/10.1109/icassp49660.2025.10890812"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890812","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890812","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/A5101492652","display_name":"Zixiang Wan","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zixiang Wan","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,School of Computer Science,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,School of Computer Science,Beijing,China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055713575","display_name":"Ziyue Qiu","orcid":null},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ziyue Qiu","raw_affiliation_strings":["Arizona State University,Ira A. Fulton Schools of Engineering,Tempe,United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University,Ira A. Fulton Schools of Engineering,Tempe,United States","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100729169","display_name":"Yiyang Liu","orcid":"https://orcid.org/0000-0002-5846-7354"},"institutions":[{"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":"Yiyang Liu","raw_affiliation_strings":["Tsinghua University,Xingjian College,Beijing,China,100084"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Xingjian College,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100692904","display_name":"Wei-Qiang Zhang","orcid":"https://orcid.org/0000-0003-3841-1959"},"institutions":[{"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-Qiang Zhang","raw_affiliation_strings":["Tsinghua University,Department of Electronic Engineering,Beijing,China,100084"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Electronic Engineering,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9836000204086304,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9836000204086304,"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/T10860","display_name":"Speech and Audio Processing","score":0.9556999802589417,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.916100025177002,"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/metadata","display_name":"Metadata","score":0.8209155797958374},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.756858229637146},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.6261312961578369},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5644309520721436},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.5307443141937256},{"id":"https://openalex.org/keywords/stage","display_name":"Stage (stratigraphy)","score":0.4938112199306488},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.16597983241081238}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.8209155797958374},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.756858229637146},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.6261312961578369},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5644309520721436},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5307443141937256},{"id":"https://openalex.org/C146357865","wikidata":"https://www.wikidata.org/wiki/Q1123245","display_name":"Stage (stratigraphy)","level":2,"score":0.4938112199306488},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.16597983241081238},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890812","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890812","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":[{"display_name":"Reduced inequalities","score":0.46000000834465027,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2127141656","https://openalex.org/W2140801466","https://openalex.org/W2146334809","https://openalex.org/W2918559346","https://openalex.org/W2962799344","https://openalex.org/W2972424567","https://openalex.org/W3002223612","https://openalex.org/W3167533889","https://openalex.org/W3200913068","https://openalex.org/W3208480086","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3210314098","https://openalex.org/W3212314299","https://openalex.org/W4225635674","https://openalex.org/W4283016277","https://openalex.org/W4285144981","https://openalex.org/W4372266023","https://openalex.org/W4372266717","https://openalex.org/W4372269797","https://openalex.org/W4372341110","https://openalex.org/W4375869114","https://openalex.org/W4375869336","https://openalex.org/W4385822433","https://openalex.org/W4385822510","https://openalex.org/W4385822669","https://openalex.org/W4385822715","https://openalex.org/W4385823320","https://openalex.org/W4392902665","https://openalex.org/W4392902798","https://openalex.org/W6766978945","https://openalex.org/W6771876938"],"related_works":["https://openalex.org/W2058118494","https://openalex.org/W2392768766","https://openalex.org/W2382021449","https://openalex.org/W2095118173","https://openalex.org/W2106424170","https://openalex.org/W1985426483","https://openalex.org/W2501188010","https://openalex.org/W4299935056","https://openalex.org/W3126677997","https://openalex.org/W1610857240"],"abstract_inverted_index":{"Speech":[0],"Emotion":[1],"Recognition":[2],"(SER)":[3],"involves":[4],"analyzing":[5],"vocal":[6],"expressions":[7],"to":[8,104,113],"determine":[9],"the":[10,16,57,85,98,111,144],"emotional":[11],"state":[12],"of":[13,21,69,87,95],"speakers,":[14],"where":[15],"comprehensive":[17],"and":[18,118,129],"thorough":[19],"utilization":[20],"audio":[22],"information":[23,117],"is":[24,101],"paramount.":[25],"Therefore,":[26],"we":[27,55],"propose":[28],"a":[29,48],"novel":[30],"approach":[31,133],"on":[32,139],"self-supervised":[33],"learning":[34],"(SSL)":[35],"models":[36,128,138],"that":[37,91],"employs":[38],"all":[39,79],"available":[40],"auxiliary":[41,89,123],"information\u2014":[42],"specifically":[43],"metadata\u2014to":[44],"enhance":[45],"performance.":[46],"Through":[47],"two-stage":[49],"fine-tuning":[50],"method":[51],"in":[52,67],"multi-task":[53],"learning,":[54],"introduce":[56],"Augmented":[58],"Residual":[59],"Integration":[60],"(ARI)":[61],"module,":[62],"which":[63],"enhances":[64],"transformer":[65],"layers":[66],"encoder":[68],"SSL":[70,141],"models.":[71],"The":[72],"module":[73,100],"efficiently":[74],"preserves":[75],"acoustic":[76],"features":[77],"across":[78],"different":[80],"levels,":[81],"thereby":[82],"significantly":[83],"improving":[84],"performance":[86],"metadata-related":[88,122],"tasks":[90],"require":[92],"various":[93],"levels":[94],"features.":[96],"Moreover,":[97],"Co-attention":[99],"incorporated":[102],"due":[103],"its":[105],"complementary":[106],"nature":[107],"with":[108],"ARI,":[109],"enabling":[110],"model":[112],"effectively":[114],"utilize":[115],"multidimensional":[116],"contextual":[119],"relationships":[120],"from":[121],"tasks.":[124],"Under":[125],"pre-trained":[126],"base":[127],"speaker-independent":[130],"setup,":[131],"our":[132],"consistently":[134],"surpasses":[135],"state-of-the-art":[136],"(SOTA)":[137],"multiple":[140],"encoders":[142],"for":[143],"IEMOCAP":[145],"dataset.":[146]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-18T07:39:51.176621","created_date":"2025-10-10T00:00:00"}