{"id":"https://openalex.org/W7148351998","doi":"https://doi.org/10.1109/asru65441.2025.11434744","title":"EmoBiMamba-TTS: Bidirectional State Space Model for Emotion-Intensity Controllable Text-to-Speech","display_name":"EmoBiMamba-TTS: Bidirectional State Space Model for Emotion-Intensity Controllable Text-to-Speech","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148351998","doi":"https://doi.org/10.1109/asru65441.2025.11434744"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434744","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434744","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5003847195","display_name":"Insung Ham","orcid":null},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Insung Ham","raw_affiliation_strings":["Korea University,Department of Electrical and Electronic Engineering,Seoul,South Korea"],"affiliations":[{"raw_affiliation_string":"Korea University,Department of Electrical and Electronic Engineering,Seoul,South Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113955841","display_name":"Bonwha Ku","orcid":null},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Bonwha Ku","raw_affiliation_strings":["Korea University,Department of Electrical and Electronic Engineering,Seoul,South Korea"],"affiliations":[{"raw_affiliation_string":"Korea University,Department of Electrical and Electronic Engineering,Seoul,South Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132783996","display_name":"Hanseok Ko","orcid":null},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hanseok Ko","raw_affiliation_strings":["Korea University,Department of Electrical and Electronic Engineering,Seoul,South Korea"],"affiliations":[{"raw_affiliation_string":"Korea University,Department of Electrical and Electronic Engineering,Seoul,South Korea","institution_ids":["https://openalex.org/I197347611"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5003847195"],"corresponding_institution_ids":["https://openalex.org/I197347611"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.81545604,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.8601999878883362,"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":0.8601999878883362,"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/T12031","display_name":"Speech and dialogue systems","score":0.021400000900030136,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.017100000753998756,"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/control-theory","display_name":"Control theory (sociology)","score":0.44190001487731934},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.41769999265670776},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.39800000190734863},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.3540000021457672},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.3176000118255615},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.28790000081062317}],"concepts":[{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.44190001487731934},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.43540000915527344},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.41769999265670776},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.3984000086784363},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.39800000190734863},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.3540000021457672},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3197000026702881},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3176000118255615},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.28790000081062317},{"id":"https://openalex.org/C52918065","wikidata":"https://www.wikidata.org/wiki/Q230945","display_name":"State-space representation","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C184720557","wikidata":"https://www.wikidata.org/wiki/Q7825049","display_name":"Topology (electrical circuits)","level":2,"score":0.27320000529289246},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.25609999895095825},{"id":"https://openalex.org/C36299963","wikidata":"https://www.wikidata.org/wiki/Q1369844","display_name":"Observability","level":2,"score":0.25600001215934753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434744","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434744","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1967745743","https://openalex.org/W2519091744","https://openalex.org/W2962834855","https://openalex.org/W2963163163","https://openalex.org/W3008691130","https://openalex.org/W3015338123","https://openalex.org/W3016160783","https://openalex.org/W3097777922","https://openalex.org/W3097828251","https://openalex.org/W3174977508","https://openalex.org/W3196308991","https://openalex.org/W3196782138","https://openalex.org/W4205742757","https://openalex.org/W4225956675","https://openalex.org/W4246744310","https://openalex.org/W4313316128","https://openalex.org/W4366493008","https://openalex.org/W4372340836","https://openalex.org/W4375869364","https://openalex.org/W4385245566","https://openalex.org/W4385822379","https://openalex.org/W4385993826","https://openalex.org/W4402112499","https://openalex.org/W4402115961","https://openalex.org/W4402669711","https://openalex.org/W4403511013","https://openalex.org/W4407779628","https://openalex.org/W4408352482","https://openalex.org/W4410087476"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"have":[2],"led":[3],"to":[4,95],"emotion-intensity":[5],"controllable":[6],"text-to-speech":[7],"(TTS)":[8],"models.":[9],"However,":[10],"these":[11,35],"systems":[12],"often":[13],"suffer":[14],"from":[15],"degraded":[16],"speech":[17,97,113],"quality":[18,98],"and":[19,30,56,78,91,115],"unnatural":[20],"emotional":[21,76,102],"expressions,":[22],"creating":[23],"a":[24,40,88],"critical":[25],"gap":[26],"between":[27,75],"human-like":[28],"expressiveness":[29],"synthesized":[31],"speech.":[32],"To":[33],"address":[34],"challenges,":[36],"we":[37,82],"propose":[38],"EmoBiMamba-TTS,":[39],"TTS":[41],"framework":[42],"that":[43,107],"replaces":[44],"Transformer":[45],"architectures":[46],"with":[47],"Bidirectional":[48],"State":[49],"Space":[50],"Models":[51],"(SSMs),":[52],"enabling":[53],"linear-time":[54],"processing":[55],"robust":[57],"context":[58],"modeling.":[59],"Our":[60],"approach":[61],"incorporates":[62],"Emotion-Guided":[63],"Cross":[64],"Attention":[65],"(EGCA)":[66],"for":[67],"fine-grained":[68],"emotion":[69],"intensity":[70],"control":[71],"by":[72],"modeling":[73],"interactions":[74],"cues":[77],"acoustic":[79],"features.":[80],"Additionally,":[81],"introduce":[83],"dual":[84],"discriminative":[85],"learning":[86],"via":[87],"Joint":[89],"Conditional":[90],"Unconditional":[92],"(JCU)":[93],"discriminator":[94],"enhance":[96],"while":[99],"preserving":[100],"natural":[101],"expressions.":[103],"Experimental":[104],"results":[105],"demonstrate":[106],"EmoBiMamba-TTS":[108],"outperforms":[109],"existing":[110],"baselines":[111],"in":[112],"naturalness":[114],"computational":[116],"efficiency.":[117]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-04-03T00:00:00"}