# Matcha-TTS: A fast TTS architecture with conditional flow matching ##### [Shivam Mehta][shivam_profile], [Ruibo Tu][ruibo_profile], [Jonas Beskow][jonas_profile], [Éva Székely][eva_profile], and [Gustav Eje Henter][gustav_profile] We propose Matcha-TTS, a new approach to non-autoregressive neural TTS, that uses conditional flow matching to speed up ODE-based speech synthesis. Our method: - Is probabilistic - Has compact memory footprint - Sounds highly natural - Is very fast to synthesise from Please check out the audio examples below and read our arXiv preprint for more details. Code and pre-trained models will be made available shortly after the ICASSP deadline. [shivam_profile]: https://www.kth.se/profile/smehta [ruibo_profile]: https://www.kth.se/profile/ruibo [jonas_profile]: https://www.kth.se/profile/beskow [eva_profile]: https://www.kth.se/profile/szekely [gustav_profile]: https://people.kth.se/~ghe/ [this_page]: https://shivammehta25.github.io/Diff-TTSG/ ## Architecture Architecture of OverFlow ## Stimuli from the evaluation test Currently loaded => MAT-10 : Sentence 1

It had established periodic regular review of the status of four hundred individuals;

Architecture Condition Sentence 1 Sentence 2 Sentence 3 Sentence 4 Sentence 5 Sentence 6
Vocoded VOC
Matcha-TTS MAT-10
MAT-4
MAT-2
Grad-TTS GRAD-10
GRAD-4
Grad-TTS+CFM GCFM-4
FastSpeech FS2
VITS VITS