Picture for Éva Székely

Éva Székely

Should you use a probabilistic duration model in TTS? Probably! Especially for spontaneous speech

Add code
Jun 08, 2024
Viaarxiv icon

Evaluating Text-to-Speech Synthesis from a Large Discrete Token-based Speech Language Model

Add code
May 16, 2024
Viaarxiv icon

Unified speech and gesture synthesis using flow matching

Add code
Oct 08, 2023
Viaarxiv icon

Matcha-TTS: A fast TTS architecture with conditional flow matching

Add code
Sep 06, 2023
Viaarxiv icon

On the Use of Self-Supervised Speech Representations in Spontaneous Speech Synthesis

Add code
Jul 11, 2023
Viaarxiv icon

Diff-TTSG: Denoising probabilistic integrated speech and gesture synthesis

Add code
Jun 15, 2023
Figure 1 for Diff-TTSG: Denoising probabilistic integrated speech and gesture synthesis
Figure 2 for Diff-TTSG: Denoising probabilistic integrated speech and gesture synthesis
Figure 3 for Diff-TTSG: Denoising probabilistic integrated speech and gesture synthesis
Viaarxiv icon

Automatic Evaluation of Turn-taking Cues in Conversational Speech Synthesis

Add code
May 29, 2023
Viaarxiv icon

A Comparative Study of Self-Supervised Speech Representations in Read and Spontaneous TTS

Add code
Mar 05, 2023
Viaarxiv icon

Prosody-controllable spontaneous TTS with neural HMMs

Add code
Nov 24, 2022
Viaarxiv icon

OverFlow: Putting flows on top of neural transducers for better TTS

Add code
Nov 13, 2022
Viaarxiv icon