{"id":"https://openalex.org/W4405709162","doi":"https://doi.org/10.1109/iscslp63861.2024.10800183","title":"Hola-TTS: A Cross-Lingual Zero-Shot Text-to-Speech System for Chinese, English, Japanese, and Korean","display_name":"Hola-TTS: A Cross-Lingual Zero-Shot Text-to-Speech System for Chinese, English, Japanese, and Korean","publication_year":2024,"publication_date":"2024-11-07","ids":{"openalex":"https://openalex.org/W4405709162","doi":"https://doi.org/10.1109/iscslp63861.2024.10800183"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp63861.2024.10800183","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800183","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5113430879","display_name":"Hongwu Ding","orcid":null},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hongwu Ding","raw_affiliation_strings":["School of Computer Science and Technology, Anhui University,Hefei"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Anhui University,Hefei","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102566429","display_name":"Yiquan Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiquan Zhou","raw_affiliation_strings":["School of Software Engineering, Xi'an Jiaotong University,Xi'an"],"affiliations":[{"raw_affiliation_string":"School of Software Engineering, Xi'an Jiaotong University,Xi'an","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115694877","display_name":"Wenyu Wang","orcid":"https://orcid.org/0009-0005-3970-7040"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenyu Wang","raw_affiliation_strings":["School of Software Engineering, Xi'an Jiaotong University,Xi'an"],"affiliations":[{"raw_affiliation_string":"School of Software Engineering, Xi'an Jiaotong University,Xi'an","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109749734","display_name":"JiaCheng Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"JiaCheng Xu","raw_affiliation_strings":["School of Computer Science and Technology, Anhui University,Hefei"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Anhui University,Hefei","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003168564","display_name":"Jiaqi Mei","orcid":"https://orcid.org/0000-0003-2449-8037"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaqi Mei","raw_affiliation_strings":["School of Computer Science and Technology, Anhui University,Hefei"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Anhui University,Hefei","institution_ids":["https://openalex.org/I143868143"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5113430879"],"corresponding_institution_ids":["https://openalex.org/I143868143"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21261206,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"601","last_page":"605"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9908999800682068,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9908999800682068,"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/T10028","display_name":"Topic Modeling","score":0.9593999981880188,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9559999704360962,"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/computer-science","display_name":"Computer science","score":0.6532645225524902},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.6328227519989014},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5231146216392517},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4698917865753174},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.46016284823417664},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38376715779304504},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.298947274684906},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.07114693522453308}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6532645225524902},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6328227519989014},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5231146216392517},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4698917865753174},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.46016284823417664},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38376715779304504},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.298947274684906},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.07114693522453308},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","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/iscslp63861.2024.10800183","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800183","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7400000095367432,"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":20,"referenced_works":["https://openalex.org/W2752796333","https://openalex.org/W2963750251","https://openalex.org/W3198694222","https://openalex.org/W3203407300","https://openalex.org/W4252812408","https://openalex.org/W4307323391","https://openalex.org/W4385822293","https://openalex.org/W4402112533","https://openalex.org/W4402672020","https://openalex.org/W4405709275","https://openalex.org/W6763832098","https://openalex.org/W6783867762","https://openalex.org/W6796464841","https://openalex.org/W6805710207","https://openalex.org/W6810681707","https://openalex.org/W6848735303","https://openalex.org/W6850334629","https://openalex.org/W6852870047","https://openalex.org/W6853096648","https://openalex.org/W6857062747"],"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/W3204019825"],"abstract_inverted_index":{"This":[0,120],"paper":[1],"presents":[2],"Hola-TTS,":[3],"a":[4,26,31,43,52,73,123],"novel":[5],"cross-lingual":[6,88,135],"zero-shot":[7,138],"text-to-speech":[8],"system":[9],"capable":[10],"of":[11,76,113],"synthesizing":[12],"speech":[13,78,128],"in":[14,126,137],"Chinese,":[15],"English,":[16],"Japanese,":[17],"and":[18,36,50,81,102,134],"Korean.":[19],"We":[20,140],"introduce":[21],"several":[22],"key":[23],"innovations,":[24],"including":[25],"comprehensive":[27],"data":[28],"cleaning":[29],"process,":[30],"multilingual":[32,127],"phoneme":[33],"representation":[34],"strategy,":[35],"an":[37],"improved":[38,131],"model":[39,69],"architecture.":[40],"Hola-TTS":[41,95],"employs":[42],"fully":[44],"autoregressive":[45],"method":[46],"for":[47],"token":[48],"generation":[49],"utilizes":[51],"delay":[53],"parttern":[54],"approach,":[55],"which":[56],"significantly":[57],"enhance":[58,87],"dependencies":[59],"between":[60],"different":[61],"codebooks":[62],"at":[63,148],"the":[64,111,146],"same":[65],"time":[66],"step.":[67],"Our":[68],"is":[70],"trained":[71],"on":[72],"diverse":[74],"set":[75],"cleaned":[77],"recognition":[79],"datasets":[80],"uses":[82],"phoneme-level":[83],"language":[84],"label":[85],"to":[86,118,143,145],"synthesis":[89],"capabilities.":[90],"Comparative":[91],"evaluations":[92],"demonstrate":[93],"that":[94],"outperforms":[96],"state-of-the-art":[97],"models":[98],"like":[99],"VALL-E":[100],"X":[101],"X-TTS":[103],"across":[104],"various":[105],"metrics.":[106],"Ablation":[107],"studies":[108],"further":[109],"confirm":[110],"effectiveness":[112],"our":[114],"proposed":[115],"improvements":[116],"compare":[117],"VoiceCraft.":[119],"work":[121],"represents":[122],"significant":[124],"advancement":[125],"synthesis,":[129],"offering":[130],"quality,":[132],"consistency,":[133],"capabilities":[136],"TTS.":[139],"encourage":[141],"readers":[142],"listen":[144],"demos":[147],"https://holatts.aithub.io/":[149]},"counts_by_year":[],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}