{"id":"https://openalex.org/W4403791830","doi":"https://doi.org/10.1145/3664647.3681044","title":"FlashSpeech: Efficient Zero-Shot Speech Synthesis","display_name":"FlashSpeech: Efficient Zero-Shot Speech Synthesis","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791830","doi":"https://doi.org/10.1145/3664647.3681044"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681044","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681044","pdf_url":null,"source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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/A5019978970","display_name":"Zhen Ye","orcid":"https://orcid.org/0009-0003-6932-9859"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Zhen Ye","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073017662","display_name":"Zeqian Ju","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zeqian Ju","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089924305","display_name":"Haohe Liu","orcid":"https://orcid.org/0000-0003-1036-7888"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Haohe Liu","raw_affiliation_strings":["University of Surrey, Surrey, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Surrey, Surrey, United Kingdom","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101522530","display_name":"Xu Tan","orcid":"https://orcid.org/0000-0001-5631-0639"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Tan","raw_affiliation_strings":["Microsoft, BeiJing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft, BeiJing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046262750","display_name":"Jianyi Chen","orcid":"https://orcid.org/0009-0002-7690-5570"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jianyi Chen","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113190721","display_name":"Yiwen Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yiwen Lu","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114416557","display_name":"Peiwen Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Peiwen Sun","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046174250","display_name":"Jiahao Pan","orcid":"https://orcid.org/0000-0001-9724-6645"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jiahao Pan","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113307475","display_name":"Weizhen Bian","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]},{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK","SG"],"is_corresponding":false,"raw_author_name":"Weizhen Bian","raw_affiliation_strings":["Hong Kong University of Science and Technology & National University of Singapore, Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology & National University of Singapore, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109763938","display_name":"S. He","orcid":"https://orcid.org/0009-0005-8369-6350"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Shulin He","raw_affiliation_strings":["Hong Kong University of Science and Technology & Inner Mongolia University, Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology & Inner Mongolia University, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I2722730","https://openalex.org/I200769079","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100652844","display_name":"Wei Xue","orcid":"https://orcid.org/0000-0002-4942-7748"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Wei Xue","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061082180","display_name":"Qifeng Liu","orcid":"https://orcid.org/0009-0003-1526-8173"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Qifeng Liu","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045081171","display_name":"Yike Guo","orcid":"https://orcid.org/0000-0002-3075-2161"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yike Guo","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":13,"corresponding_author_ids":["https://openalex.org/A5019978970"],"corresponding_institution_ids":["https://openalex.org/I200769079"],"apc_list":null,"apc_paid":null,"fwci":2.0672,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.89095579,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"6998","last_page":"7007"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9988999962806702,"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":0.9923999905586243,"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":0.6509109735488892},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6057047247886658},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.5433562397956848},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5043584108352661},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07591956853866577},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.07320880889892578}],"concepts":[{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6509109735488892},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6057047247886658},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5433562397956848},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5043584108352661},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07591956853866577},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.07320880889892578},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3664647.3681044","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681044","pdf_url":null,"source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-140623","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-140623","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2056716515","https://openalex.org/W2105910985","https://openalex.org/W2903739847","https://openalex.org/W3015449694","https://openalex.org/W3180355996","https://openalex.org/W3203407300","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3217030260","https://openalex.org/W4225956675","https://openalex.org/W4226332109","https://openalex.org/W4281969232","https://openalex.org/W4312933868","https://openalex.org/W4385571941","https://openalex.org/W4386132131","https://openalex.org/W4393156644","https://openalex.org/W4401042918","https://openalex.org/W6748655329"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","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"],"abstract_inverted_index":{"Recent":[0],"progress":[1],"in":[2,182,212],"large-scale":[3,56],"zero-shot":[4,57,152,174],"speech":[5,30,58,120,153,175,201,205],"synthesis":[6,31,59,176],"has":[7],"been":[8],"significantly":[9],"advanced":[10],"by":[11,194],"language":[12],"models":[13],"and":[14,26,80,144,187,203],"diffusion":[15,99],"models.":[16],"However,":[17],"the":[18,65,76,94,102,111,116,119,148,159],"generation":[19,125],"process":[20],"of":[21,64,113,118,127,162,184],"both":[22],"methods":[23],"is":[24,73],"slow":[25],"computationally":[27],"intensive.":[28],"Efficient":[29],"using":[32],"a":[33,46,55,82,97,105],"lower":[34],"computing":[35],"budget":[36],"to":[37,147],"achieve":[38],"quality":[39,143,186],"on":[40,75],"par":[41],"with":[42,61,69,133],"previous":[43,70],"work":[44],"remains":[45],"significant":[47],"challenge.":[48],"In":[49],"this":[50],"paper,":[51],"we":[52],"present":[53],"FlashSpeech,":[54],"system":[60],"approximately":[62],"5%":[63],"inference":[66],"time":[67],"compared":[68],"work.":[71],"FlashSpeech":[72,128,165,190],"built":[74],"latent":[77],"consistency":[78,85],"model":[79,100],"applies":[81],"novel":[83],"adversarial":[84],"training":[86],"approach":[87],"that":[88],"can":[89,129,166,209],"train":[90],"from":[91],"scratch":[92],"without":[93],"need":[95],"for":[96,151],"pre-trained":[98],"as":[101],"teacher.":[103],"Furthermore,":[104,189],"new":[106],"prosody":[107],"generator":[108],"module":[109],"enhances":[110],"diversity":[112],"prosody,":[114],"making":[115],"rhythm":[117],"sound":[121],"more":[122],"natural.":[123],"The":[124],"processes":[126],"be":[130,167,210],"achieved":[131],"efficiently":[132,195],"one":[134],"or":[135],"two":[136],"sampling":[137],"steps":[138],"while":[139,178],"maintaining":[140,179],"high":[141,145],"audio":[142,149],"similarity":[146],"prompt":[150],"generation.":[154],"Our":[155],"experimental":[156],"results":[157],"demonstrate":[158],"superior":[160],"performance":[161,181],"FlashSpeech.":[163],"Notably,":[164],"about":[168],"20":[169],"times":[170],"faster":[171],"than":[172],"other":[173],"systems":[177],"comparable":[180],"terms":[183],"voice":[185,199],"similarity.":[188],"demonstrates":[191],"its":[192],"versatility":[193],"performing":[196],"tasks":[197],"like":[198],"conversion,":[200],"editing,":[202],"diverse":[204],"sampling.":[206],"Audio":[207],"samples":[208],"found":[211],"https://flashspeech.github.io/":[213]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}