{"id":"https://openalex.org/W4391021721","doi":"https://doi.org/10.1109/asru57964.2023.10389766","title":"E3 TTS: Easy End-to-End Diffusion-Based Text To Speech","display_name":"E3 TTS: Easy End-to-End Diffusion-Based Text To Speech","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021721","doi":"https://doi.org/10.1109/asru57964.2023.10389766"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389766","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389766","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5101437985","display_name":"Yuan Gao","orcid":"https://orcid.org/0000-0002-8428-034X"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yuan Gao","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111040545","display_name":"Nobuyuki Morioka","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nobuyuki Morioka","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092339709","display_name":"Yu Zhang","orcid":"https://orcid.org/0009-0007-7826-1306"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu Zhang","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049929716","display_name":"Nanxin Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nanxin Chen","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101437985"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":1.7483,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.88084946,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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/T11309","display_name":"Music and Audio Processing","score":0.9990000128746033,"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/T10028","display_name":"Topic Modeling","score":0.9962999820709229,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7982512712478638},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.7513077855110168},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.6720132827758789},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6595188975334167},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.6146237254142761},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6003490090370178},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5235785245895386},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.4957197904586792},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.47693294286727905},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.42805197834968567},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3597913086414337},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.15781623125076294}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7982512712478638},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7513077855110168},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.6720132827758789},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6595188975334167},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.6146237254142761},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6003490090370178},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5235785245895386},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.4957197904586792},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.47693294286727905},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.42805197834968567},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3597913086414337},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.15781623125076294},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru57964.2023.10389766","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389766","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2120847449","https://openalex.org/W2125838338","https://openalex.org/W2515943672","https://openalex.org/W2760103357","https://openalex.org/W2896457183","https://openalex.org/W2903739847","https://openalex.org/W2913668833","https://openalex.org/W2914304175","https://openalex.org/W2946200149","https://openalex.org/W2963609956","https://openalex.org/W2972478942","https://openalex.org/W3036167779","https://openalex.org/W3091928890","https://openalex.org/W3110257065","https://openalex.org/W3161296985","https://openalex.org/W3161782335","https://openalex.org/W3196705076","https://openalex.org/W3198769980","https://openalex.org/W4220890336","https://openalex.org/W4224035735","https://openalex.org/W4281485151","https://openalex.org/W4297841480","https://openalex.org/W4301206121","https://openalex.org/W4313679638","https://openalex.org/W4318350327","https://openalex.org/W4320169845","https://openalex.org/W4372259881","https://openalex.org/W4375869198","https://openalex.org/W4375869257","https://openalex.org/W4381786045","https://openalex.org/W4386076458","https://openalex.org/W4390872669","https://openalex.org/W6679045638","https://openalex.org/W6748409065","https://openalex.org/W6749555683","https://openalex.org/W6750489868","https://openalex.org/W6756159577","https://openalex.org/W6763832098","https://openalex.org/W6765779288","https://openalex.org/W6778823374","https://openalex.org/W6779337556","https://openalex.org/W6779823529","https://openalex.org/W6782760101","https://openalex.org/W6783182287","https://openalex.org/W6784545093","https://openalex.org/W6786375611","https://openalex.org/W6795261426","https://openalex.org/W6809885388","https://openalex.org/W6838639034","https://openalex.org/W6848735303","https://openalex.org/W6849744127","https://openalex.org/W6849953009"],"related_works":["https://openalex.org/W4313443006","https://openalex.org/W2998781440","https://openalex.org/W2945374968","https://openalex.org/W4385452045","https://openalex.org/W4293777179","https://openalex.org/W2164070813","https://openalex.org/W2135608140","https://openalex.org/W2895525995","https://openalex.org/W4224231624","https://openalex.org/W2332512904"],"abstract_inverted_index":{"We":[0],"propose":[1],"Easy":[2],"End-to-End":[3],"Diffusion-based":[4],"Text":[5],"to":[6,90],"Speech,":[7],"a":[8,117],"simple":[9],"and":[10,26],"efficient":[11],"end-to-end":[12],"text-to-speech":[13],"model":[14],"based":[15],"on":[16,45,71],"diffusion.":[17],"E3":[18,40,56,75,88,107],"TTS":[19,41,57,76,89,108,120],"directly":[20],"takes":[21],"plain":[22],"text":[23],"as":[24,98],"input":[25],"generates":[27],"an":[28,32],"audio":[29],"waveform":[30,64],"through":[31,65],"iterative":[33],"refinement":[34],"process.":[35,68],"Unlike":[36],"many":[37],"prior":[38],"work,":[39],"does":[42],"not":[43],"rely":[44],"any":[46,101],"intermediate":[47],"representations":[48],"like":[49],"spectrogram":[50],"features":[51],"or":[52],"alignment":[53],"information.":[54],"Instead,":[55],"models":[58],"the":[59,63,66,83,114],"temporal":[60],"structure":[61,81],"of":[62,116],"diffusion":[67],"Without":[69],"relying":[70],"additional":[72,102],"conditioning":[73],"information,":[74],"could":[77],"support":[78],"flexible":[79],"latent":[80],"within":[82],"given":[84],"audio.":[85],"This":[86],"enables":[87],"be":[91],"easily":[92],"adapted":[93],"for":[94],"zero-shot":[95],"tasks":[96],"such":[97],"editing":[99],"without":[100],"training.":[103],"Experiments":[104],"show":[105],"that":[106],"can":[109],"generate":[110],"high-fidelity":[111],"audio,":[112],"approaching":[113],"performance":[115],"state-of-the-art":[118],"neural":[119],"system.":[121],"Audio":[122],"samples":[123],"are":[124],"available":[125],"at":[126],"https://e3tts.github.io.":[127]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}