{"id":"https://openalex.org/W4391021646","doi":"https://doi.org/10.1109/asru57964.2023.10389638","title":"Zero-Shot Emotion Transfer for Cross-Lingual Speech Synthesis","display_name":"Zero-Shot Emotion Transfer for Cross-Lingual Speech Synthesis","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021646","doi":"https://doi.org/10.1109/asru57964.2023.10389638"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389638","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389638","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5100697206","display_name":"Yuke Li","orcid":"https://orcid.org/0009-0009-5806-7228"},"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&#x2019;an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;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&#x2019;an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013928267","display_name":"Yi Lei","orcid":"https://orcid.org/0000-0002-9256-9311"},"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":"Yi Lei","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100429403","display_name":"Hai Li","orcid":"https://orcid.org/0000-0003-3228-6544"},"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","iQIYI Inc., Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iQIYI Inc.,Chengdu,China","institution_ids":["https://openalex.org/I4210115040"]},{"raw_affiliation_string":"iQIYI Inc., Chengdu, China","institution_ids":["https://openalex.org/I4210115040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100640524","display_name":"Junhui Liu","orcid":"https://orcid.org/0000-0003-2259-2273"},"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","iQIYI Inc., Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iQIYI Inc.,Chengdu,China","institution_ids":["https://openalex.org/I4210115040"]},{"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","iQIYI Inc., Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iQIYI Inc.,Chengdu,China","institution_ids":["https://openalex.org/I4210115040"]},{"raw_affiliation_string":"iQIYI Inc., Chengdu, China","institution_ids":["https://openalex.org/I4210115040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"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&#x2019;an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9962999820709229,"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/T11309","display_name":"Music and Audio Processing","score":0.9524000287055969,"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/zero","display_name":"Zero (linguistics)","score":0.7214469909667969},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.6118062734603882},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6009297966957092},{"id":"https://openalex.org/keywords/transfer","display_name":"Transfer (computing)","score":0.5147697925567627},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47881728410720825},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3201519548892975},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.17283794283866882},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.11771813035011292}],"concepts":[{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.7214469909667969},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.6118062734603882},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6009297966957092},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.5147697925567627},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47881728410720825},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3201519548892975},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.17283794283866882},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.11771813035011292},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","level":1,"score":0.0},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru57964.2023.10389638","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389638","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6000000238418579}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W1570629387","https://openalex.org/W1959608418","https://openalex.org/W2139751012","https://openalex.org/W2904459034","https://openalex.org/W2963609956","https://openalex.org/W2972473628","https://openalex.org/W2973084242","https://openalex.org/W3007067948","https://openalex.org/W3015826515","https://openalex.org/W3024869864","https://openalex.org/W3033411150","https://openalex.org/W3036601975","https://openalex.org/W3048217770","https://openalex.org/W3092028330","https://openalex.org/W3095012670","https://openalex.org/W3095790275","https://openalex.org/W3122349645","https://openalex.org/W3128910262","https://openalex.org/W3161436426","https://openalex.org/W3197642003","https://openalex.org/W3197668461","https://openalex.org/W3197704090","https://openalex.org/W3198858531","https://openalex.org/W3206725777","https://openalex.org/W3207558756","https://openalex.org/W3209059054","https://openalex.org/W4210777104","https://openalex.org/W4226380987","https://openalex.org/W4233300967","https://openalex.org/W4280542470","https://openalex.org/W4311000453","https://openalex.org/W4366493008","https://openalex.org/W4372260365","https://openalex.org/W4378105483","https://openalex.org/W4388579593","https://openalex.org/W4389519363","https://openalex.org/W4391892546","https://openalex.org/W4395957972","https://openalex.org/W6640963894","https://openalex.org/W6750489868","https://openalex.org/W6778823374","https://openalex.org/W6780218876","https://openalex.org/W6783867762","https://openalex.org/W6790220310","https://openalex.org/W6795807602","https://openalex.org/W6802591955","https://openalex.org/W6803425590","https://openalex.org/W6839013216","https://openalex.org/W6847363464","https://openalex.org/W6852290182","https://openalex.org/W6852575346","https://openalex.org/W6852909395"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W4298312966","https://openalex.org/W2325697621"],"abstract_inverted_index":{"Zero-shot":[0],"emotion":[1,10,124],"transfer":[2,9],"in":[3,16,24,40,141],"cross-lingual":[4,98],"speech":[5,14,23,79,145],"synthesis":[6],"aims":[7],"to":[8,20,65,91,126],"from":[11,109],"an":[12],"arbitrary":[13],"reference":[15],"the":[17,21,25,42,51,67,77,93,96,137,147],"source":[18],"language":[19],"synthetic":[22,97],"target":[26,149],"language.":[27],"Building":[28,49],"such":[29],"a":[30,84,110],"system":[31],"faces":[32],"challenges":[33,60],"of":[34,46,95],"unnatural":[35],"foreign":[36],"accents":[37],"and":[38,71],"difficulty":[39],"modeling":[41,125],"shared":[43,101],"emotional":[44,73,102,144,152],"expressions":[45,74],"different":[47,105,132],"languages.":[48,133],"on":[50],"DelightfulTTS":[52],"[1]":[53],"neural":[54],"architecture,":[55],"this":[56],"paper":[57],"addresses":[58],"these":[59],"by":[61,83],"introducing":[62],"specifically-designed":[63],"modules":[64],"model":[66,113],"language-specific":[68,78],"prosody":[69,80],"features":[70],"language-shared":[72],"separately.":[75],"Specifically,":[76],"is":[81,107],"learned":[82],"non-autoregressive":[85],"predictive":[86],"coding":[87],"(NPC)":[88],"module":[89],"[2]":[90],"improve":[92],"naturalness":[94],"speech.":[99],"The":[100],"expression":[103],"between":[104],"languages":[106],"extracted":[108],"pre-trained":[111],"self-supervised":[112],"Hu":[114],"BERT":[115],"with":[116],"strong":[117],"generalization":[118],"capabilities.":[119],"We":[120],"further":[121],"use":[122],"hierarchical":[123],"capture":[127],"more":[128],"comprehensive":[129],"emotions":[130],"across":[131],"Experimental":[134],"results":[135],"demonstrate":[136],"proposed":[138],"framework\u2019s":[139],"effectiveness":[140],"synthesizing":[142],"bi-lingual":[143],"for":[146],"monolingual":[148],"speaker":[150],"without":[151],"training":[153],"data":[154],"<sup":[155,159],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[156,160],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[157,161],".":[158],"Speech":[162],"samples:":[163],"https://ykli22.github.io/ZSET/":[164]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
