{"id":"https://openalex.org/W4399657366","doi":"https://doi.org/10.48550/arxiv.2406.07855","title":"VALL-E R: Robust and Efficient Zero-Shot Text-to-Speech Synthesis via Monotonic Alignment","display_name":"VALL-E R: Robust and Efficient Zero-Shot Text-to-Speech Synthesis via Monotonic Alignment","publication_year":2024,"publication_date":"2024-06-12","ids":{"openalex":"https://openalex.org/W4399657366","doi":"https://doi.org/10.48550/arxiv.2406.07855"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2406.07855","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.07855","pdf_url":"https://arxiv.org/pdf/2406.07855","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/2406.07855","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100767961","display_name":"Bing Han","orcid":"https://orcid.org/0009-0009-1821-6161","observed_orcids":["https://orcid.org/0009-0009-1821-6161"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han, Bing","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106557565","display_name":"Long Zhou","orcid":"https://orcid.org/0009-0006-1919-4943","observed_orcids":["https://orcid.org/0009-0006-1919-4943"]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhou, Long","raw_affiliation_strings":["Microsoft Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101635405","display_name":"Shujie Liu","orcid":"https://orcid.org/0009-0008-2599-6752","observed_orcids":["https://orcid.org/0009-0008-2599-6752"]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liu, Shujie","raw_affiliation_strings":["Microsoft Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079533447","display_name":"Sanyuan Chen","orcid":"https://orcid.org/0000-0002-3082-6052","observed_orcids":["https://orcid.org/0000-0002-3082-6052"]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen, Sanyuan","raw_affiliation_strings":["Microsoft Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031382920","display_name":"Lingwei Meng","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meng, Lingwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114177065","display_name":"Yanming Qian","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qian, Yanming","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102928467","display_name":"Yanqing Liu","orcid":"https://orcid.org/0000-0002-8484-4723","observed_orcids":["https://orcid.org/0000-0002-8484-4723"]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liu, Yanqing","raw_affiliation_strings":["Microsoft Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100329353","display_name":"Sheng Zhao","orcid":"https://orcid.org/0000-0002-9624-5381","observed_orcids":["https://orcid.org/0000-0002-9624-5381","https://orcid.org/0000-0003-4030-7368"]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhao, Sheng","raw_affiliation_strings":["Microsoft Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100365053","display_name":"Jinyu Li","orcid":"https://orcid.org/0000-0002-1089-9748","observed_orcids":["https://orcid.org/0000-0002-1089-9748"]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li, Jinyu","raw_affiliation_strings":["Microsoft Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014662947","display_name":"Furu Wei","orcid":"https://orcid.org/0000-0002-7810-5852","observed_orcids":["https://orcid.org/0000-0002-7810-5852"]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei, Furu","raw_affiliation_strings":["Microsoft Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":5,"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":0.9994999766349792,"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":0.9994999766349792,"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":0.0003000000142492354,"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":0.0,"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-shot-text-to-speech","display_name":"zero-shot text-to-speech","score":0.925000011920929},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.781000018119812},{"id":"https://openalex.org/keywords/downsampling","display_name":"downsampling","score":0.4740000069141388},{"id":"https://openalex.org/keywords/inference-efficiency","display_name":"inference efficiency","score":0.7570000290870667}],"concepts":[{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.7299935221672058},{"id":"https://openalex.org/C72169020","wikidata":"https://www.wikidata.org/wiki/Q194404","display_name":"Monotonic function","level":2,"score":0.6670655012130737},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4896745979785919},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4275575280189514},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3284572958946228},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.14923787117004395},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.08754011988639832},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.07454782724380493}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2406.07855","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.07855","pdf_url":"https://arxiv.org/pdf/2406.07855","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.2406.07855","doi":"https://doi.org/10.48550/arxiv.2406.07855","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2406.07855","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:2406.07855","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.07855","pdf_url":"https://arxiv.org/pdf/2406.07855","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399657366.pdf","grobid_xml":"https://content.openalex.org/works/W4399657366.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4394007232","https://openalex.org/W4313679638","https://openalex.org/W4399554695","https://openalex.org/W4415981656","https://openalex.org/W4409362648","https://openalex.org/W4406461672","https://openalex.org/W7081566042","https://openalex.org/W4415540898","https://openalex.org/W4379924545","https://openalex.org/W4415085369"],"abstract_inverted_index":{"With":[0],"the":[1,48,60,82,96,110,126,135,140,163,185,194],"help":[2],"of":[3,52,63,84,143,165,196],"discrete":[4,127],"neural":[5],"audio":[6,53],"codecs,":[7],"large":[8],"language":[9],"models":[10],"(LLM)":[11],"have":[12],"increasingly":[13],"been":[14],"recognized":[15],"as":[16,41],"a":[17,73,89,104,121],"promising":[18],"methodology":[19],"for":[20,198],"zero-shot":[21,77],"Text-to-Speech":[22],"(TTS)":[23],"synthesis.":[24],"However,":[25],"sampling":[26,50],"based":[27],"decoding":[28,136],"strategies":[29],"bring":[30],"astonishing":[31],"diversity":[32],"to":[33,59,94,113,124,187,190],"generation,":[34],"but":[35],"also":[36,54],"pose":[37],"robustness":[38,160],"issues":[39],"such":[40],"typos,":[42],"omissions":[43],"and":[44,75,100,156],"repetition.":[45],"In":[46,168],"addition,":[47,169],"high":[49,141],"rate":[51],"brings":[55],"huge":[56],"computational":[57],"overhead":[58],"inference":[61],"process":[62],"autoregression.":[64],"To":[65],"address":[66],"these":[67,148],"issues,":[68],"we":[69,87,119],"propose":[70],"VALL-E":[71,150],"R,":[72],"robust":[74],"efficient":[76],"TTS":[78],"system,":[79],"building":[80],"upon":[81],"foundation":[83],"VALL-E.":[85],"Specifically,":[86],"introduce":[88],"phoneme":[90],"monotonic":[91],"alignment":[92,107],"strategy":[93],"strengthen":[95],"connection":[97],"between":[98],"phonemes":[99,155],"acoustic":[101,111],"sequence,":[102],"ensuring":[103],"more":[105],"precise":[106],"by":[108,161,201],"constraining":[109],"tokens":[112],"match":[114],"their":[115],"associated":[116],"phonemes.":[117],"Furthermore,":[118],"employ":[120],"codec-merging":[122],"approach":[123],"downsample":[125],"codes":[128],"in":[129],"shallow":[130],"quantization":[131],"layer,":[132],"thereby":[133],"accelerating":[134],"speed":[137],"while":[138],"preserving":[139],"quality":[142],"speech":[144,197],"output.":[145],"Benefiting":[146],"from":[147],"strategies,":[149],"R":[151],"obtains":[152],"controllablity":[153],"over":[154,176],"demonstrates":[157],"its":[158],"strong":[159],"approaching":[162],"WER":[164],"ground":[166],"truth.":[167],"it":[170],"requires":[171],"fewer":[172],"autoregressive":[173],"steps,":[174],"with":[175],"60%":[177],"time":[178],"reduction":[179],"during":[180],"inference.":[181],"This":[182],"research":[183],"has":[184],"potential":[186],"be":[188,206],"applied":[189],"meaningful":[191],"projects,":[192],"including":[193],"creation":[195],"those":[199],"affected":[200],"aphasia.":[202],"Audio":[203],"samples":[204],"will":[205],"available":[207],"at:":[208],"https://aka.ms/valler.":[209]},"counts_by_year":[{"year":2025,"cited_by_count":5}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2024-06-14T00:00:00"}