VITS, Tacotron or FastSpeech? Challenging some of the most popular synthesizers

Show simple item record
dc.contributor.authorMatoušek, Jindřich
dc.contributor.authorTihelka, Daniel
dc.contributor.authorTihelková, Alice
dc.date.accessioned2025-06-20T08:55:19Z
dc.date.available2025-06-20T08:55:19Z
dc.date.issued2023
dc.date.updated2025-06-20T08:55:19Z
dc.description.abstractThe paper presents a comparative study of three neural speech synthesizers, namely VITS, Tacotron$2$ and FastSpeech$2$, which belong among the most popular TTS systems nowadays. Due to their varying nature, they have been tested from several points of view, analysing not only the overall quality of the synthesized speech, but also the capability of processing either orthographic or phonetic inputs. The analysis has been carried out on two English and one Czech voices.en
dc.format14
dc.identifier.doi10.1007/978-3-031-47665-5_26
dc.identifier.isbn978-3-031-47664-8
dc.identifier.issn0302-9743
dc.identifier.obd43940621
dc.identifier.orcidMatoušek, Jindřich 0000-0002-7408-7730
dc.identifier.orcidTihelka, Daniel 0000-0002-3149-2330
dc.identifier.orcidTihelková, Alice 0000-0002-3367-4525
dc.identifier.urihttp://hdl.handle.net/11025/61570
dc.language.isoen
dc.project.IDSGS-2022-017
dc.project.IDGA22-27800S
dc.project.ID90140
dc.project.ID90104
dc.publisherSpringer
dc.relation.ispartofseries7th Asian Conference on Pattern Recognition (ACPR 2023)
dc.subjecttext-to-speech synthesis, VITS, FastSpeech2, Tacotron2en
dc.titleVITS, Tacotron or FastSpeech? Challenging some of the most popular synthesizersen
dc.typeStať ve sborníku (D)
dc.typeSTAŤ VE SBORNÍKU
dc.type.statusPublished Version
local.files.count1*
local.files.size309766*
local.has.filesyes*
local.identifier.eid2-s2.0-85177460227

Files

Original bundle
Showing 1 - 1 out of 1 results
No Thumbnail Available
Name:
Matousek_Tihelka_Tihelkova_VITS_Tacotron_or_FastSpeech_Challenging_Some_of_the_Most_Popular_Synthesizers_2023.pdf
Size:
302.51 KB
Format:
Adobe Portable Document Format
Download
License bundle
Showing 1 - 1 out of 1 results
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Conference Papers (KKY)