{"id":"https://openalex.org/W7204171963","doi":"https://doi.org/10.48550/arxiv.2608.22399","title":"Dual-Scale State-Space Modeling with Speaker-Wise Dynamic CRF for Speech Emotion Recognition in Conversation","display_name":"Dual-Scale State-Space Modeling with Speaker-Wise Dynamic CRF for Speech Emotion Recognition in Conversation","publication_year":2026,"publication_date":"2026-08-23","ids":{"openalex":"https://openalex.org/W7204171963","doi":"https://doi.org/10.48550/arxiv.2608.22399"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.22399","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.22399","pdf_url":"https://arxiv.org/pdf/2608.22399","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.22399","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111925886","display_name":"Guan-Hua Wen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wen, Guan-Hua","raw_affiliation_strings":["Department of Computer Science and Information Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148114463","display_name":"Hou-Chiang Tseng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I154864474","display_name":"National Taiwan University of Science and Technology","ror":"https://ror.org/00q09pe49","country_code":"TW","type":"education","lineage":["https://openalex.org/I154864474"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Tseng, Hou-Chiang","raw_affiliation_strings":["Graduate Institute of Digital Learning and Education National Taiwan University of Science and Technology , Taipei , Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate Institute of Digital Learning and Education National Taiwan University of Science and Technology , Taipei , Taiwan","institution_ids":["https://openalex.org/I154864474"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5151823567","display_name":"Kuan-Yu Chen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Kuan-Yu","raw_affiliation_strings":["Department of Computer Science and Information Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9824000000953674,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.9824000000953674,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.014999999664723873,"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":0.0006000000284984708,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/state-space-models","display_name":"state-space model","score":0.7319999933242798},{"id":"https://openalex.org/keywords/self-supervised-speech-representations","display_name":"self-supervised speech representations","score":0.843999981880188},{"id":"https://openalex.org/keywords/iemocap","display_name":"IEMOCAP","score":0.7179999947547913},{"id":"https://openalex.org/keywords/meld","display_name":"MELD","score":1.0}],"concepts":[{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.6985999941825867},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6726999878883362},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6699000000953674},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.6108999848365784},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5986999869346619},{"id":"https://openalex.org/C194232998","wikidata":"https://www.wikidata.org/wiki/Q1606712","display_name":"Transition (genetics)","level":3,"score":0.5594000220298767},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.5558000206947327},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5454000234603882},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.49459999799728394},{"id":"https://openalex.org/C2776035688","wikidata":"https://www.wikidata.org/wiki/Q1606558","display_name":"Affect (linguistics)","level":2,"score":0.4339999854564667},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42100000381469727},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.41339999437332153},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.40689998865127563},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3582000136375427},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.3564999997615814},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.3517000079154968},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.3328000009059906},{"id":"https://openalex.org/C2777853878","wikidata":"https://www.wikidata.org/wiki/Q743569","display_name":"Phonetic transcription","level":2,"score":0.32600000500679016},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3098999857902527},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.3059000074863434},{"id":"https://openalex.org/C117379686","wikidata":"https://www.wikidata.org/wiki/Q6996459","display_name":"Viterbi decoder","level":3,"score":0.3043000102043152},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.30160000920295715},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.2888000011444092},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.28529998660087585},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.2777999937534332},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2757999897003174},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C206310091","wikidata":"https://www.wikidata.org/wiki/Q750859","display_name":"Emotion classification","level":2,"score":0.27149999141693115}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.22399","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.22399","pdf_url":"https://arxiv.org/pdf/2608.22399","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.22399","doi":"https://doi.org/10.48550/arxiv.2608.22399","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.22399","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.22399","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.22399","pdf_url":"https://arxiv.org/pdf/2608.22399","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204171963.pdf","grobid_xml":"https://content.openalex.org/works/W7204171963.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4411302324","https://openalex.org/W7213451423","https://openalex.org/W4402979574","https://openalex.org/W4319452886","https://openalex.org/W2972965453","https://openalex.org/W4412985033","https://openalex.org/W2202011751","https://openalex.org/W4375868946","https://openalex.org/W4385822846","https://openalex.org/W7165664424"],"abstract_inverted_index":{"Conversational":[0],"speech":[1,39],"emotion":[2,20,107,120,130],"recognition":[3],"must":[4],"reconcile":[5],"acoustic":[6],"evidence":[7],"across":[8],"temporal":[9],"scales":[10],"with":[11,90],"two":[12,96],"interaction":[13],"processes:":[14],"cross-speaker":[15],"contextual":[16,119],"influence":[17],"and":[18,43,53,136,141,144,157],"within-speaker":[19],"evolution.":[21],"We":[22],"propose":[23],"DSSM-CRF,":[24],"an":[25,66],"audio-only":[26],"architecture":[27],"that":[28],"explicitly":[29],"separates":[30],"these":[31],"processes.":[32],"Bidirectional":[33],"state-space":[34],"models":[35],"encode":[36],"fused":[37],"self-supervised":[38],"representations":[40],"at":[41],"frame":[42],"dialogue":[44],"scales,":[45],"so":[46],"each":[47,62,104],"utterance":[48],"representation":[49],"captures":[50],"local":[51],"prosody":[52],"context":[54],"from":[55,94,154],"all":[56],"speakers.":[57],"The":[58],"decoder":[59],"then":[60],"orders":[61],"speaker's":[63,77,129],"utterances":[64,74],"into":[65],"independent":[67],"dynamic":[68],"conditional":[69],"random":[70],"field":[71],"chain.":[72],"Consecutive":[73],"in":[75,112,127],"a":[76,80,86,91],"chain":[78],"form":[79],"transition":[81,88],"pair":[82,105],"whose":[83],"score":[84],"combines":[85],"corpus-level":[87],"matrix":[89],"residual":[92],"predicted":[93],"the":[95],"contextualized":[97],"utterances.":[98],"An":[99],"auxiliary":[100],"objective":[101],"supervises":[102],"whether":[103],"changes":[106],"but":[108],"does":[109],"not":[110],"participate":[111],"Viterbi":[113],"inference.":[114],"Thus,":[115],"interlocutor":[116],"turns":[117],"affect":[118],"scores":[121],"without":[122],"being":[123],"treated":[124],"as":[125],"transitions":[126],"another":[128],"trajectory.":[131],"DSSM-CRF":[132],"achieves":[133],"75.81%":[134],"UA":[135],"74.90%":[137],"WA":[138,143],"on":[139,147],"IEMOCAP,":[140],"54.72%":[142],"49.31%":[145],"WF1":[146],"MELD.":[148],"Matched":[149],"controls":[150],"demonstrate":[151],"complementary":[152],"gains":[153],"speaker-wise":[155],"factorization":[156],"CRF":[158],"modeling.":[159]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-26T00:00:00"}