{"id":"https://openalex.org/W4391620705","doi":"https://doi.org/10.1109/taslp.2024.3363444","title":"METTS: Multilingual Emotional Text-to-Speech by Cross-Speaker and Cross-Lingual Emotion Transfer","display_name":"METTS: Multilingual Emotional Text-to-Speech by Cross-Speaker and Cross-Lingual Emotion Transfer","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4391620705","doi":"https://doi.org/10.1109/taslp.2024.3363444"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3363444","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3363444","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/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":["Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi&#x0027;an, China"],"raw_orcid":"https://orcid.org/0000-0001-9275-523X","affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi&#x0027;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":["Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi&#x0027;an, China"],"raw_orcid":"https://orcid.org/0000-0002-9256-9311","affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi&#x0027;an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055592507","display_name":"Tao Li","orcid":"https://orcid.org/0000-0001-5578-3960"},"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":"Tao Li","raw_affiliation_strings":["Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi&#x0027;an, China"],"raw_orcid":"https://orcid.org/0000-0001-5578-3960","affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi&#x0027;an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060467975","display_name":"Yongmao Zhang","orcid":"https://orcid.org/0009-0000-0526-5778"},"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":"Yongmao Zhang","raw_affiliation_strings":["Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi&#x0027;an, China"],"raw_orcid":"https://orcid.org/0009-0000-0526-5778","affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi&#x0027;an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110823442","display_name":"Hongbin Zhou","orcid":"https://orcid.org/0009-0005-7569-1197"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongbin Zhou","raw_affiliation_strings":["Ximalaya Inc., Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0005-7569-1197","affiliations":[{"raw_affiliation_string":"Ximalaya Inc., Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100618443","display_name":"Heng Lu","orcid":"https://orcid.org/0009-0009-9236-8825"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Heng Lu","raw_affiliation_strings":["Ximalaya Inc., Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0009-9236-8825","affiliations":[{"raw_affiliation_string":"Ximalaya Inc., Shanghai, China","institution_ids":[]}]},{"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":["Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi&#x0027;an, China"],"raw_orcid":"https://orcid.org/0000-0001-8234-0823","affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi&#x0027;an, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":10.4338,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.98599806,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"32","issue":null,"first_page":"1506","last_page":"1518"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9983999729156494,"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/T10863","display_name":"Voice and Speech Disorders","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5740975141525269},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5655513405799866},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4837894141674042},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38120248913764954},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34244781732559204}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5740975141525269},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5655513405799866},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4837894141674042},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38120248913764954},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34244781732559204}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2024.3363444","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3363444","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7900000214576721,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":75,"referenced_works":["https://openalex.org/W59175527","https://openalex.org/W1537481423","https://openalex.org/W1580555281","https://openalex.org/W1994198923","https://openalex.org/W2051217765","https://openalex.org/W2123864036","https://openalex.org/W2133665775","https://openalex.org/W2187089797","https://openalex.org/W2471520273","https://openalex.org/W2494654097","https://openalex.org/W2508171154","https://openalex.org/W2525997790","https://openalex.org/W2770743791","https://openalex.org/W2787378487","https://openalex.org/W2794448670","https://openalex.org/W2903739847","https://openalex.org/W2962691331","https://openalex.org/W2963609956","https://openalex.org/W2963964591","https://openalex.org/W2972473628","https://openalex.org/W2973177731","https://openalex.org/W3024869864","https://openalex.org/W3094785744","https://openalex.org/W3095012670","https://openalex.org/W3096514088","https://openalex.org/W3097777922","https://openalex.org/W3135644023","https://openalex.org/W3161109662","https://openalex.org/W3161436426","https://openalex.org/W3161782335","https://openalex.org/W3194347141","https://openalex.org/W3197478142","https://openalex.org/W3197659778","https://openalex.org/W3197668461","https://openalex.org/W3198048667","https://openalex.org/W3198082505","https://openalex.org/W3198213150","https://openalex.org/W3198694222","https://openalex.org/W3203164699","https://openalex.org/W3203407300","https://openalex.org/W3205316472","https://openalex.org/W3206725777","https://openalex.org/W4210433094","https://openalex.org/W4210777104","https://openalex.org/W4221146604","https://openalex.org/W4224931727","https://openalex.org/W4225303561","https://openalex.org/W4225939199","https://openalex.org/W4226332109","https://openalex.org/W4226421465","https://openalex.org/W4294311176","https://openalex.org/W4295957212","https://openalex.org/W4296069156","https://openalex.org/W4297841615","https://openalex.org/W4297841883","https://openalex.org/W4366493008","https://openalex.org/W4372260365","https://openalex.org/W4375868833","https://openalex.org/W4385245566","https://openalex.org/W4395957972","https://openalex.org/W6746238782","https://openalex.org/W6749555683","https://openalex.org/W6749761576","https://openalex.org/W6750489868","https://openalex.org/W6763832098","https://openalex.org/W6767111847","https://openalex.org/W6790220310","https://openalex.org/W6791353385","https://openalex.org/W6795807602","https://openalex.org/W6796464841","https://openalex.org/W6802119844","https://openalex.org/W6802591955","https://openalex.org/W6803547063","https://openalex.org/W6810982492","https://openalex.org/W6846143095"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Previous":[0],"multilingual":[1],"text-to-speech":[2],"(TTS)":[3],"approaches":[4,19],"have":[5,20],"considered":[6],"leveraging":[7],"monolingual":[8],"speaker":[9,161],"data":[10],"to":[11,28,62,85,110,123,153,181],"enable":[12],"cross-lingual":[13,33,64,93,188],"speech":[14,26,56,66,125],"synthesis.":[15],"However,":[16],"such":[17],"data-efficient":[18],"ignored":[21],"synthesizing":[22],"emotional":[23],"aspects":[24],"of":[25,31,40,160,196],"due":[27],"the":[29,37,55,101,106,112,154,164,193],"challenges":[30],"cross-speaker":[32,91],"emotion":[34,74,94,121,136,185],"transfer":[35],"\u2013":[36],"heavy":[38],"entanglement":[39],"<italic":[41,46,50,118,147,171],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[42,47,51,119,148,172],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">speaker":[43],"timbre</i>":[44],",":[45],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">emotion</i>":[48],"and":[49,72,92,104,129,134,184],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">language</i>":[52],"factors":[53],"in":[54,163,187],"signal":[57,156],"will":[58],"make":[59],"a":[60,79,141,167],"system":[61],"produce":[63],"synthetic":[65,189],"with":[67],"an":[68],"undesired":[69],"foreign":[70,113],"accent":[71,114],"weak":[73],"expressiveness.":[75],"This":[76],"paper":[77],"proposes":[78,105],"Multilingual":[80],"Emotional":[81],"TTS":[82],"(METTS)":[83],"model":[84,103],"mitigate":[86],"these":[87],"problems,":[88],"realizing":[89],"both":[90],"transfer.":[95],"Specifically,":[96],"METTS":[97,116],"takes":[98],"DelightfulTTS":[99],"as":[100,140],"backbone":[102],"following":[107],"designs.":[108],"First,":[109],"alleviate":[111],"problem,":[115],"introduces":[117],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">multi-scale":[120],"modeling</i>":[122],"disentangle":[124],"prosody":[126],"into":[127],"coarse-grained":[128],"fine-grained":[130],"scales,":[131],"producing":[132],"language-agnostic":[133],"language-specific":[135],"representations,":[137],"respectively.":[138],"Second,":[139],"pre-processing":[142],"step,":[143],"formant":[144],"shift":[145],"based":[146,170],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">information":[149],"perturbation</i>":[150],"is":[151,175],"applied":[152],"reference":[155,178],"for":[157,177],"better":[158],"disentanglement":[159],"timbre":[162],"speech.":[165,190],"Third,":[166],"vector":[168],"quantization":[169],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">emotion":[173],"matcher</i>":[174],"designed":[176],"selection,":[179],"leading":[180],"decent":[182],"naturalness":[183],"diversity":[186],"Experiments":[191],"demonstrate":[192],"good":[194],"design":[195],"METTS.":[197]},"counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":9}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-10T00:00:00"}