{"id":"https://openalex.org/W4400518537","doi":"https://doi.org/10.48550/arxiv.2407.05407","title":"CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens","display_name":"CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens","publication_year":2024,"publication_date":"2024-07-07","ids":{"openalex":"https://openalex.org/W4400518537","doi":"https://doi.org/10.48550/arxiv.2407.05407"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2407.05407","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.05407","pdf_url":"https://arxiv.org/pdf/2407.05407","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2407.05407","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001133136","display_name":"Zhihao Du","orcid":"https://orcid.org/0000-0003-3509-9322","observed_orcids":["https://orcid.org/0000-0003-3509-9322"]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Du, Zhihao","raw_affiliation_strings":["Speech Lab , Alibaba Group , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Lab , Alibaba Group , China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100428456","display_name":"Qian Chen","orcid":"https://orcid.org/0000-0002-1909-302X","observed_orcids":["https://orcid.org/0000-0002-1909-302X","https://orcid.org/0000-0002-1968-441X"]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen, Qian","raw_affiliation_strings":["Speech Lab , Alibaba Group , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Lab , Alibaba Group , China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101777591","display_name":"Shiliang Zhang","orcid":"https://orcid.org/0000-0002-9524-1602","observed_orcids":["https://orcid.org/0000-0002-9524-1602"]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Shiliang","raw_affiliation_strings":["Speech Lab , Alibaba Group , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Lab , Alibaba Group , China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048675276","display_name":"Kai Hu","orcid":"https://orcid.org/0000-0001-7181-9935","observed_orcids":["https://orcid.org/0000-0001-7181-9935"]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hu, Kai","raw_affiliation_strings":["Speech Lab , Alibaba Group , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Lab , Alibaba Group , China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100618443","display_name":"Heng Lu","orcid":"https://orcid.org/0009-0009-9236-8825","observed_orcids":["https://orcid.org/0009-0009-9236-8825"]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lu, Heng","raw_affiliation_strings":["Speech Lab , Alibaba Group , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Lab , Alibaba Group , China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yang, Yexin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang, Yexin","raw_affiliation_strings":["Speech Lab , Alibaba Group , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Lab , Alibaba Group , China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113284738","display_name":"Hangrui Hu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hu, Hangrui","raw_affiliation_strings":["Speech Lab , Alibaba Group , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Lab , Alibaba Group , China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zheng, Siqi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng, Siqi","raw_affiliation_strings":["Speech Lab , Alibaba Group , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Lab , Alibaba Group , China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104035474","display_name":"Yue Gu","orcid":"https://orcid.org/0009-0009-9950-2548","observed_orcids":["https://orcid.org/0009-0009-9950-2548"]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gu, Yue","raw_affiliation_strings":["Speech Lab , Alibaba Group , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Lab , Alibaba Group , China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100438492","display_name":"Ziyang Ma","orcid":"https://orcid.org/0000-0002-8195-3262","observed_orcids":["https://orcid.org/0000-0002-8195-3262"]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ma, Ziyang","raw_affiliation_strings":["Speech Lab , Alibaba Group , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Lab , Alibaba Group , China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024223042","display_name":"Zhifu Gao","orcid":"https://orcid.org/0009-0008-5691-7324","observed_orcids":["https://orcid.org/0009-0008-5691-7324"]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gao, Zhifu","raw_affiliation_strings":["Speech Lab , Alibaba Group , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Lab , Alibaba Group , China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101554221","display_name":"Zhijie Yan","orcid":"https://orcid.org/0000-0001-7147-392X","observed_orcids":["https://orcid.org/0000-0001-7147-392X"]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan, Zhijie","raw_affiliation_strings":["Speech Lab , Alibaba Group , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Lab , Alibaba Group , China","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I45928872"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":22,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":9.999999747378752e-05,"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/T10863","display_name":"Voice and Speech Disorders","score":0.0,"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/text-to-speech","display_name":"text-to-speech","score":0.8889999985694885},{"id":"https://openalex.org/keywords/zero-shot-speech-synthesis","display_name":"zero-shot speech synthesis","score":0.7450000047683716},{"id":"https://openalex.org/keywords/multilingual-speech-recognition","display_name":"multilingual speech recognition","score":0.7059999704360962},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"vector quantization","score":0.9729999899864197},{"id":"https://openalex.org/keywords/flow-matching","display_name":"flow matching","score":0.6579999923706055},{"id":"https://openalex.org/keywords/voice-cloning","display_name":"voice cloning","score":0.7360000014305115}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7360809445381165},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6241772174835205},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6027509570121765},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6010391116142273},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5471783876419067},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47678661346435547},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.44411104917526245},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4432174861431122},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2285255491733551},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.09145084023475647},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","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":2,"locations":[{"id":"pmh:oai:arXiv.org:2407.05407","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.05407","pdf_url":"https://arxiv.org/pdf/2407.05407","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2407.05407","doi":"https://doi.org/10.48550/arxiv.2407.05407","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2407.05407","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2407.05407","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.05407","pdf_url":"https://arxiv.org/pdf/2407.05407","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4400518537.pdf","grobid_xml":"https://content.openalex.org/works/W4400518537.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4415085369","https://openalex.org/W4392904511","https://openalex.org/W7083693352","https://openalex.org/W7202372919","https://openalex.org/W4393969253","https://openalex.org/W4415337135","https://openalex.org/W4399657366","https://openalex.org/W4408353402","https://openalex.org/W4412353446","https://openalex.org/W4402112475"],"abstract_inverted_index":{"Recent":[0],"years":[1],"have":[2],"witnessed":[3],"a":[4,49,58,100,119,134],"trend":[5],"that":[6,145,169],"large":[7],"language":[8],"model":[9,104,138],"(LLM)":[10],"based":[11],"text-to-speech":[12],"(TTS)":[13],"emerges":[14],"into":[15,33,109,200],"the":[16,82,110,114,175,179,185,192],"mainstream":[17],"due":[18],"to":[19,52,81,89,195],"their":[20],"high":[21],"naturalness":[22],"and":[23,46,79,133,159],"zero-shot":[24,121,163],"capacity.":[25],"In":[26,84],"this":[27,85,190],"paradigm,":[28],"speech":[29,55,66,91,102,198],"signals":[30],"are":[31,37,68,97],"discretized":[32],"token":[34],"sequences,":[35],"which":[36,74,96,125],"modeled":[38],"by":[39,48,105],"an":[40,71,128],"LLM":[41,129],"with":[42,92],"text":[43],"as":[44],"prompts":[45],"reconstructed":[47],"token-based":[50],"vocoder":[51],"waveforms.":[53],"Obviously,":[54],"tokens":[56,67,148,153,199],"play":[57],"critical":[59],"role":[60],"in":[61,70,154],"LLM-based":[62],"TTS":[63,122,201],"models.":[64,202],"Current":[65],"learned":[69],"unsupervised":[72,152],"manner,":[73],"lacks":[75],"explicit":[76],"semantic":[77,94,147],"information":[78],"alignment":[80],"text.":[83],"paper,":[86],"we":[87,116,167],"propose":[88,118],"represent":[90],"supervised":[93,146,197],"tokens,":[95,115],"derived":[98],"from":[99],"multilingual":[101],"recognition":[103],"inserting":[106],"vector":[107],"quantization":[108],"encoder.":[111],"Based":[112],"on":[113],"further":[117,173],"scalable":[120,180],"synthesizer,":[123],"CosyVoice,":[124],"consists":[126],"of":[127,156,182,187],"for":[130,139,162],"text-to-token":[131],"generation":[132],"conditional":[135],"flow":[136],"matching":[137],"token-to-speech":[140],"synthesis.":[141],"Experimental":[142],"results":[143],"show":[144],"significantly":[149],"outperform":[150],"existing":[151],"terms":[155],"content":[157],"consistency":[158],"speaker":[160],"similarity":[161],"voice":[164],"cloning.":[165],"Moreover,":[166],"find":[168],"utilizing":[170],"large-scale":[171],"data":[172],"improves":[174],"synthesis":[176],"performance,":[177],"indicating":[178],"capacity":[181],"CosyVoice.":[183],"To":[184],"best":[186],"our":[188],"knowledge,":[189],"is":[191],"first":[193],"attempt":[194],"involve":[196]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":21}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2024-07-11T00:00:00"}
