{"id":"https://openalex.org/W7148413014","doi":"https://doi.org/10.1109/asru65441.2025.11434682","title":"XEmoRAG: Cross-Lingual Emotion Transfer with Controllable Intensity Using Retrieval-Augmented Generation","display_name":"XEmoRAG: Cross-Lingual Emotion Transfer with Controllable Intensity Using Retrieval-Augmented Generation","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148413014","doi":"https://doi.org/10.1109/asru65441.2025.11434682"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434682","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434682","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/A5109071109","display_name":"Tianlun Zuo","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tianlun Zuo","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi’an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028087115","display_name":"Jiaxi Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingbin Hu","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi’an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132797450","display_name":"Yuke Li","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuke Li","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi’an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101883211","display_name":"Xinfa Zhu","orcid":"https://orcid.org/0000-0001-9275-523X"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinfa Zhu","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi’an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132793713","display_name":"Hai Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210115040","display_name":"iQIYI (China)","ror":"https://ror.org/026xvz038","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210115040"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hai Li","raw_affiliation_strings":["iQIYI, Inc,Chengdu,China"],"affiliations":[{"raw_affiliation_string":"iQIYI, Inc,Chengdu,China","institution_ids":["https://openalex.org/I4210115040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132821799","display_name":"Ying Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210115040","display_name":"iQIYI (China)","ror":"https://ror.org/026xvz038","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210115040"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Yan","raw_affiliation_strings":["iQIYI, Inc,Chengdu,China"],"affiliations":[{"raw_affiliation_string":"iQIYI, Inc,Chengdu,China","institution_ids":["https://openalex.org/I4210115040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063059495","display_name":"Junhui Liu","orcid":"https://orcid.org/0000-0001-9583-4283"},"institutions":[{"id":"https://openalex.org/I4210115040","display_name":"iQIYI (China)","ror":"https://ror.org/026xvz038","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210115040"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junhui Liu","raw_affiliation_strings":["iQIYI, Inc,Chengdu,China"],"affiliations":[{"raw_affiliation_string":"iQIYI, Inc,Chengdu,China","institution_ids":["https://openalex.org/I4210115040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000506857","display_name":"Danming Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I4210115040","display_name":"iQIYI (China)","ror":"https://ror.org/026xvz038","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210115040"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Danming Xie","raw_affiliation_strings":["iQIYI, Inc,Chengdu,China"],"affiliations":[{"raw_affiliation_string":"iQIYI, Inc,Chengdu,China","institution_ids":["https://openalex.org/I4210115040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132823306","display_name":"Lei Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi’an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5109071109"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.81910443,"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":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.5921000242233276,"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":0.5921000242233276,"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":0.20569999516010284,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.029500000178813934,"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/stress","display_name":"Stress (linguistics)","score":0.5281999707221985},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.4839000105857849},{"id":"https://openalex.org/keywords/emotion-classification","display_name":"Emotion classification","score":0.48260000348091125},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.4821000099182129},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4616999924182892},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4368000030517578},{"id":"https://openalex.org/keywords/transfer","display_name":"Transfer (computing)","score":0.4097999930381775},{"id":"https://openalex.org/keywords/pitch-contour","display_name":"Pitch contour","score":0.40869998931884766}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.614300012588501},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5995000004768372},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.5281999707221985},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.4839000105857849},{"id":"https://openalex.org/C206310091","wikidata":"https://www.wikidata.org/wiki/Q750859","display_name":"Emotion classification","level":2,"score":0.48260000348091125},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.4821000099182129},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4616999924182892},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4537000060081482},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4368000030517578},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.4097999930381775},{"id":"https://openalex.org/C2777895490","wikidata":"https://www.wikidata.org/wiki/Q7198848","display_name":"Pitch contour","level":2,"score":0.40869998931884766},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.39800000190734863},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36340001225471497},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3553999960422516},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.3531999886035919},{"id":"https://openalex.org/C2779178101","wikidata":"https://www.wikidata.org/wiki/Q6987274","display_name":"Negative transfer","level":3,"score":0.35100001096725464},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.33059999346733093},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.323199987411499},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.31470000743865967},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2955000102519989},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.2838999927043915},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2775999903678894},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.2766000032424927},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.27459999918937683},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.25540000200271606}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434682","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434682","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":0.7418809533119202,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2972473628","https://openalex.org/W3021411204","https://openalex.org/W4366493008","https://openalex.org/W4372340947","https://openalex.org/W4372346850","https://openalex.org/W4385822745","https://openalex.org/W4385823160","https://openalex.org/W4386536205","https://openalex.org/W4387021032","https://openalex.org/W4391021646","https://openalex.org/W4391620705","https://openalex.org/W4395957972","https://openalex.org/W4402112533","https://openalex.org/W4409362462","https://openalex.org/W4412945327","https://openalex.org/W4415708087","https://openalex.org/W7133222967"],"related_works":[],"abstract_inverted_index":{"Zero-shot":[0],"emotion":[1,17,54,71,111,115,171],"transfer":[2,72,112,184],"in":[3,11],"cross-lingual":[4],"speech":[5,10,23,97,162],"synthesis":[6],"refers":[7],"to":[8,35,68,75,178],"generating":[9],"a":[12,25,65,78,105,118],"target":[13],"language,":[14],"where":[15],"the":[16,36,43,50,136],"is":[18,189],"expressed":[19],"based":[20],"on":[21,86],"reference":[22,166],"from":[24,55,73,95,104],"different":[26],"source":[27],"language.":[28],"However,":[29],"this":[30,60],"task":[31],"remains":[32],"challenging":[33],"due":[34],"scarcity":[37],"of":[38,45,52],"parallel":[39,87],"multilingual":[40],"emotional":[41,88,93,107,143,150,183],"corpora,":[42],"presence":[44],"foreign":[46],"accent":[47],"artifacts,":[48],"and":[49,98,124,142,149,159,181],"difficulty":[51],"separating":[53],"language-specific":[56],"prosodic":[57],"features.":[58],"In":[59],"paper,":[61],"we":[62],"propose":[63],"XEmoRAG,":[64],"novel":[66],"framework":[67],"enable":[69],"zero-shot":[70],"Chinese":[74,96,133,165],"Thai":[76,102,137,161],"using":[77,163],"large":[79],"language":[80],"model":[81],"(LLM)-based":[82],"model,":[83],"without":[84,113,168],"relying":[85],"data.":[89],"XEmoRAG":[90,156],"extracts":[91],"language-agnostic":[92],"embeddings":[94],"retrieves":[99],"emotionally":[100],"matched":[101],"utterances":[103],"curated":[106],"database,":[108],"enabling":[109],"controllable":[110],"explicit":[114,170],"labels.":[116,172],"Additionally,":[117],"flow-matching":[119],"alignment":[120],"module":[121],"minimizes":[122],"pitch":[123],"duration":[125],"mismatches,":[126],"ensuring":[127],"natural":[128,160],"prosody.":[129],"It":[130],"also":[131],"blends":[132],"timbre":[134],"into":[135],"synthesis,":[138],"enhancing":[139],"rhythmic":[140],"accuracy":[141],"expression,":[144],"while":[145],"preserving":[146],"speaker":[147],"characteristics":[148],"consistency.":[151],"Experimental":[152],"results":[153,174],"show":[154],"that":[155],"synthesizes":[157],"expressive":[158],"only":[164],"audio,":[167],"requiring":[169],"These":[173],"highlight":[175],"XEmoRAG\u2019s":[176],"capability":[177],"achieve":[179],"flexible":[180],"low-resource":[182],"across":[185],"languages.":[186],"Our":[187],"demo":[188],"available":[190],"at":[191],"https://tlzuo-lesley.github.io/Demo-page/.":[192]},"counts_by_year":[],"updated_date":"2026-04-03T16:44:17.987007","created_date":"2026-04-03T00:00:00"}