{"id":"https://openalex.org/W4400104484","doi":"https://doi.org/10.48550/arxiv.2406.18009","title":"E2 TTS: Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS","display_name":"E2 TTS: Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS","publication_year":2024,"publication_date":"2024-06-26","ids":{"openalex":"https://openalex.org/W4400104484","doi":"https://doi.org/10.48550/arxiv.2406.18009"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2406.18009","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.18009","pdf_url":"https://arxiv.org/pdf/2406.18009","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2406.18009","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026088950","display_name":"\u015eefik Emre Eskimez","orcid":"https://orcid.org/0000-0001-6259-5925"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Eskimez, Sefik Emre","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100363446","display_name":"Xiaofei Wang","orcid":"https://orcid.org/0000-0001-6429-566X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Xiaofei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028363114","display_name":"Manthan Thakker","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thakker, Manthan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112416737","display_name":"Canrun Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Canrun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101375070","display_name":"Chung-Hsien Tsai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tsai, Chung-Hsien","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033383677","display_name":"Zhen Xiao","orcid":"https://orcid.org/0000-0003-3832-3916"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiao, Zhen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023001621","display_name":"Hemin Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Hemin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046470928","display_name":"Zirun Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Zirun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048919230","display_name":"Min Tang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Min","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101274342","display_name":"Xu Tan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tan, Xu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100360923","display_name":"Yanqing Liu","orcid":"https://orcid.org/0000-0002-4150-0680"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yanqing","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100329353","display_name":"Sheng Zhao","orcid":"https://orcid.org/0000-0002-9624-5381"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Sheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5016279564","display_name":"Naoyuki Kanda","orcid":"https://orcid.org/0000-0002-8628-3288"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kanda, Naoyuki","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":13,"corresponding_author_ids":["https://openalex.org/A5026088950"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"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/T12702","display_name":"Brain Tumor Detection and Classification","score":0.7379000186920166,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T12702","display_name":"Brain Tumor Detection and Classification","score":0.7379000186920166,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.6589999794960022,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10662","display_name":"Ultrasonics and Acoustic Wave Propagation","score":0.6561999917030334,"subfield":{"id":"https://openalex.org/subfields/2211","display_name":"Mechanics of Materials"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.7032697200775146},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.6747586727142334},{"id":"https://openalex.org/keywords/embarrassingly-parallel","display_name":"Embarrassingly parallel","score":0.6642597913742065},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3503801226615906},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.31783223152160645},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1277053952217102},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07864892482757568},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.06762927770614624}],"concepts":[{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.7032697200775146},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6747586727142334},{"id":"https://openalex.org/C126909462","wikidata":"https://www.wikidata.org/wiki/Q5369501","display_name":"Embarrassingly parallel","level":3,"score":0.6642597913742065},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3503801226615906},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.31783223152160645},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1277053952217102},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07864892482757568},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.06762927770614624},{"id":"https://openalex.org/C120373497","wikidata":"https://www.wikidata.org/wiki/Q1087987","display_name":"Parallel algorithm","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2406.18009","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.18009","pdf_url":"https://arxiv.org/pdf/2406.18009","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2406.18009","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2406.18009","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2406.18009","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.18009","pdf_url":"https://arxiv.org/pdf/2406.18009","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4400104484.pdf","grobid_xml":"https://content.openalex.org/works/W4400104484.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W1979597421","https://openalex.org/W1522943736","https://openalex.org/W2007980826","https://openalex.org/W4295122399","https://openalex.org/W2061531152","https://openalex.org/W3002753104","https://openalex.org/W2077600819","https://openalex.org/W2142036596","https://openalex.org/W2156628102"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"Embarrassingly":[3],"Easy":[4],"Text-to-Speech":[5],"(E2":[6],"TTS),":[7],"a":[8,35],"fully":[9],"non-autoregressive":[10],"zero-shot":[11,83],"text-to-speech":[12],"system":[13],"that":[14,86],"offers":[15],"human-level":[16],"naturalness":[17],"and":[18,22,96],"state-of-the-art":[19,82],"speaker":[20],"similarity":[21],"intelligibility.":[23],"In":[24],"the":[25,29,51,109],"E2":[26,79,102,117],"TTS":[27,80,84,103,118],"framework,":[28],"text":[30],"input":[31,110],"is":[32,46],"converted":[33],"into":[34],"character":[36],"sequence":[37],"with":[38],"filler":[39],"tokens.":[40],"The":[41,99],"flow-matching-based":[42],"mel":[43],"spectrogram":[44],"generator":[45],"then":[47],"trained":[48],"based":[49],"on":[50],"audio":[52],"infilling":[53],"task.":[54],"Unlike":[55],"many":[56],"previous":[57,92],"works,":[58,93],"it":[59],"does":[60],"not":[61],"require":[62],"additional":[63],"components":[64],"(e.g.,":[65,72],"duration":[66],"model,":[67],"grapheme-to-phoneme)":[68],"or":[69,90],"complex":[70],"techniques":[71],"monotonic":[73],"alignment":[74],"search).":[75],"Despite":[76],"its":[77],"simplicity,":[78],"achieves":[81],"capabilities":[85],"are":[87],"comparable":[88],"to":[89,119],"surpass":[91],"including":[94],"Voicebox":[95],"NaturalSpeech":[97],"3.":[98],"simplicity":[100],"of":[101,116],"also":[104],"allows":[105],"for":[106,126],"flexibility":[107],"in":[108],"representation.":[111],"We":[112],"propose":[113],"several":[114],"variants":[115],"improve":[120],"usability":[121],"during":[122],"inference.":[123],"See":[124],"https://aka.ms/e2tts/":[125],"demo":[127],"samples.":[128]},"counts_by_year":[],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}
