{"id":"https://openalex.org/W7148349880","doi":"https://doi.org/10.1109/asru65441.2025.11434676","title":"Speaker Style-Aware Phoneme Anchoring For Improved Cross-Lingual Speech Emotion Recognition","display_name":"Speaker Style-Aware Phoneme Anchoring For Improved Cross-Lingual Speech Emotion Recognition","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148349880","doi":"https://doi.org/10.1109/asru65441.2025.11434676"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434676","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434676","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/A5073523469","display_name":"Shreya G. Upadhyay","orcid":"https://orcid.org/0009-0000-8411-087X"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Shreya G. Upadhyay","raw_affiliation_strings":["National Tsing Hua University,Department of Electrical Engineering,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Tsing Hua University,Department of Electrical Engineering,Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040793194","display_name":"Carlos Busso","orcid":"https://orcid.org/0000-0002-4075-4072"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carlos Busso","raw_affiliation_strings":["Carnegie Mellon University,Language Technologies Institute,USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Language Technologies Institute,USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086107623","display_name":"Chi-Chun Lee","orcid":"https://orcid.org/0000-0003-0186-4321"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chi-Chun Lee","raw_affiliation_strings":["National Tsing Hua University,Department of Electrical Engineering,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Tsing Hua University,Department of Electrical Engineering,Taiwan","institution_ids":["https://openalex.org/I25846049"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5073523469"],"corresponding_institution_ids":["https://openalex.org/I25846049"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.81904633,"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":0.9832000136375427,"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":0.9832000136375427,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.00419999985024333,"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":0.00279999990016222,"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/anchoring","display_name":"Anchoring","score":0.6762999892234802},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6222000122070312},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5889999866485596},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.5882999897003174},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.42010000348091125},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4162999987602234},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.3571000099182129}],"concepts":[{"id":"https://openalex.org/C18483071","wikidata":"https://www.wikidata.org/wiki/Q168432","display_name":"Anchoring","level":2,"score":0.6762999892234802},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6222000122070312},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5889999866485596},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5882999897003174},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5602999925613403},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.536300003528595},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.42010000348091125},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4162999987602234},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.37929999828338623},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3571000099182129},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.3472999930381775},{"id":"https://openalex.org/C2779379281","wikidata":"https://www.wikidata.org/wiki/Q61895854","display_name":"Externalization","level":2,"score":0.3472999930381775},{"id":"https://openalex.org/C206310091","wikidata":"https://www.wikidata.org/wiki/Q750859","display_name":"Emotion classification","level":2,"score":0.3273000121116638},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3239000141620636},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.304500013589859},{"id":"https://openalex.org/C2988148770","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion detection","level":3,"score":0.2865999937057495},{"id":"https://openalex.org/C137584468","wikidata":"https://www.wikidata.org/wiki/Q35395","display_name":"Phonetics","level":2,"score":0.2856999933719635}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434676","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434676","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":[{"score":0.6155264377593994,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W200033050","https://openalex.org/W1668904664","https://openalex.org/W1974410405","https://openalex.org/W2000633092","https://openalex.org/W2014399678","https://openalex.org/W2019977029","https://openalex.org/W2029026153","https://openalex.org/W2064790003","https://openalex.org/W2165104163","https://openalex.org/W2243265928","https://openalex.org/W2742542661","https://openalex.org/W2786657259","https://openalex.org/W2907262790","https://openalex.org/W2924116307","https://openalex.org/W2963447013","https://openalex.org/W3086923691","https://openalex.org/W3120709499","https://openalex.org/W3140745443","https://openalex.org/W3162387328","https://openalex.org/W3166157623","https://openalex.org/W3197659778","https://openalex.org/W3209059054","https://openalex.org/W3209389523","https://openalex.org/W3209984917","https://openalex.org/W4372260053","https://openalex.org/W4375868872","https://openalex.org/W4375869457","https://openalex.org/W4387530839","https://openalex.org/W4390872742","https://openalex.org/W4390874791","https://openalex.org/W4392124182","https://openalex.org/W4392902630","https://openalex.org/W4402112182","https://openalex.org/W4406387559","https://openalex.org/W4408353312"],"related_works":[],"abstract_inverted_index":{"Cross-lingual":[0],"speech":[1],"emotion":[2,23,94,123],"recognition":[3],"(SER)":[4],"remains":[5],"a":[6,29,49],"challenging":[7],"task":[8],"due":[9],"to":[10,74,91],"differences":[11],"in":[12,86,121],"phonetic":[13,61,89],"variability":[14],"and":[15,41,62,88,103,114],"speaker-specific":[16],"expressive":[17],"styles":[18],"across":[19,38,96],"languages.":[20,42,97],"Effectively":[21],"capturing":[22],"under":[24],"such":[25],"diverse":[26],"conditions":[27],"requires":[28],"framework":[30,54],"that":[31,55],"can":[32],"align":[33],"the":[34,60,100,119],"externalization":[35],"of":[36],"emotions":[37],"different":[39],"speakers":[40],"To":[43],"address":[44],"this":[45],"problem,":[46],"we":[47,82],"propose":[48],"speaker-style":[50],"aware":[51],"phoneme":[52],"anchoring":[53,85],"aligns":[56],"emotional":[57],"expression":[58],"at":[59],"speaker":[63,69,77,87],"levels.":[64],"Our":[65],"method":[66],"builds":[67],"emotionspecific":[68],"communities":[70],"via":[71],"graph-based":[72],"clustering":[73],"capture":[75],"shared":[76],"traits.":[78],"Using":[79],"these":[80],"groups,":[81],"apply":[83],"dual-space":[84],"spaces":[90],"enable":[92],"better":[93],"transfer":[95],"Evaluations":[98],"on":[99],"MSP-Podcast":[101],"(English)":[102],"BIIC-Podcast":[104],"(Taiwanese":[105],"Mandarin)":[106],"corpora":[107],"demonstrate":[108],"improved":[109],"generalization":[110],"over":[111],"competitive":[112],"baselines":[113],"provide":[115],"valuable":[116],"insights":[117],"into":[118],"commonalities":[120],"cross-lingual":[122],"representation.":[124]},"counts_by_year":[],"updated_date":"2026-04-03T16:44:17.987007","created_date":"2026-04-03T00:00:00"}