{"id":"https://openalex.org/W4408353320","doi":"https://doi.org/10.1109/icassp49660.2025.10890230","title":"E1 TTS: Simple and Fast Non-Autoregressive TTS","display_name":"E1 TTS: Simple and Fast Non-Autoregressive TTS","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353320","doi":"https://doi.org/10.1109/icassp49660.2025.10890230"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890230","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890230","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100425929","display_name":"Zhijun Liu","orcid":"https://orcid.org/0000-0002-4679-5123"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhijun Liu","raw_affiliation_strings":["The Chinese University of Hong Kong,School of Data Science,Shenzhen,P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,School of Data Science,Shenzhen,P.R. China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100328224","display_name":"Shuai Wang","orcid":"https://orcid.org/0000-0001-6457-9478"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Wang","raw_affiliation_strings":["The Chinese University of Hong Kong,School of Data Science,Shenzhen,P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,School of Data Science,Shenzhen,P.R. China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027312746","display_name":"Pengcheng Zhu","orcid":"https://orcid.org/0000-0002-8360-2327"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengcheng Zhu","raw_affiliation_strings":["NetEase Inc.,Fuxi AI Lab,Hangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NetEase Inc.,Fuxi AI Lab,Hangzhou,China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036369578","display_name":"Mengxiao Bi","orcid":"https://orcid.org/0009-0007-6680-481X"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengxiao Bi","raw_affiliation_strings":["NetEase Inc.,Fuxi AI Lab,Hangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NetEase Inc.,Fuxi AI Lab,Hangzhou,China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["The Chinese University of Hong Kong,School of Data Science,Shenzhen,P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,School of Data Science,Shenzhen,P.R. China","institution_ids":["https://openalex.org/I4210116924"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11667","display_name":"Advanced Chemical Sensor Technologies","score":0.5464000105857849,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11667","display_name":"Advanced Chemical Sensor Technologies","score":0.5464000105857849,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/T10640","display_name":"Spectroscopy and Chemometric Analyses","score":0.4796000123023987,"subfield":{"id":"https://openalex.org/subfields/1602","display_name":"Analytical Chemistry"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.7281070351600647},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.6738889217376709},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6615964770317078},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.43175452947616577},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3869600296020508},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2112656533718109},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.16316384077072144}],"concepts":[{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.7281070351600647},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.6738889217376709},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6615964770317078},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43175452947616577},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3869600296020508},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2112656533718109},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.16316384077072144},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/icassp49660.2025.10890230","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890230","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W2591927543","https://openalex.org/W2972359262","https://openalex.org/W3015282541","https://openalex.org/W3150572638","https://openalex.org/W3196001064","https://openalex.org/W4252812408","https://openalex.org/W4304099317","https://openalex.org/W4312933868","https://openalex.org/W4375869198","https://openalex.org/W4387968164","https://openalex.org/W4388979610","https://openalex.org/W4390872297","https://openalex.org/W4391021721","https://openalex.org/W4392902860","https://openalex.org/W4392904491","https://openalex.org/W4392931781","https://openalex.org/W4393147067","https://openalex.org/W4402111456","https://openalex.org/W4402115993","https://openalex.org/W4402716152","https://openalex.org/W4402726956","https://openalex.org/W4403791830","https://openalex.org/W4406461672","https://openalex.org/W4409362648","https://openalex.org/W6763832098","https://openalex.org/W6765779288","https://openalex.org/W6779871621","https://openalex.org/W6786375611","https://openalex.org/W6791022691","https://openalex.org/W6796464841","https://openalex.org/W6796730497","https://openalex.org/W6805710207","https://openalex.org/W6809884996","https://openalex.org/W6838843145","https://openalex.org/W6843731886","https://openalex.org/W6850614898","https://openalex.org/W6852364241","https://openalex.org/W6853592262","https://openalex.org/W6858558679","https://openalex.org/W6868957684","https://openalex.org/W6869301554","https://openalex.org/W6869689521","https://openalex.org/W6869691399","https://openalex.org/W6873686716"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2051487156","https://openalex.org/W1585007175","https://openalex.org/W2073681303","https://openalex.org/W2171218219","https://openalex.org/W1972271943","https://openalex.org/W2150410159","https://openalex.org/W2382521049"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"Easy":[3],"One-Step":[4],"Text-to-Speech":[5],"(E1":[6],"TTS),":[7],"an":[8],"efficient":[9],"non-autoregressive":[10],"zero-shot":[11],"text-to-speech":[12],"system":[13],"based":[14],"on":[15],"denoising":[16],"diffusion":[17],"pretraining":[18],"and":[19,40,67],"distribution":[20],"matching":[21],"distillation.":[22],"The":[23,43],"training":[24],"of":[25,45],"E1":[26,46,63],"TTS":[27,47,64],"is":[28,48],"straightforward;":[29],"it":[30],"does":[31],"not":[32],"require":[33],"explicit":[34],"monotonic":[35],"alignment":[36],"between":[37],"the":[38],"text":[39],"audio":[41],"pairs.":[42],"inference":[44],"efficient,":[49],"requiring":[50],"only":[51],"one":[52],"neural":[53],"network":[54],"evaluation":[55],"for":[56],"each":[57],"utterance.":[58],"Despite":[59],"its":[60],"sampling":[61],"efficiency,":[62],"achieves":[65],"naturalness":[66],"speaker":[68],"similarity":[69],"comparable":[70],"to":[71],"various":[72],"strong":[73],"baseline":[74],"models.":[75],"Audio":[76],"samples":[77],"are":[78],"available":[79],"at":[80],"e1tts.github.io.":[81]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}