Picture for Kamil Pokora

Kamil Pokora

Creating New Voices using Normalizing Flows

Add code
Dec 22, 2023
Viaarxiv icon

Cross-lingual Knowledge Distillation via Flow-based Voice Conversion for Robust Polyglot Text-To-Speech

Add code
Sep 15, 2023
Viaarxiv icon

Comparing normalizing flows and diffusion models for prosody and acoustic modelling in text-to-speech

Add code
Jul 31, 2023
Viaarxiv icon

On granularity of prosodic representations in expressive text-to-speech

Add code
Jan 26, 2023
Viaarxiv icon

Remap, warp and attend: Non-parallel many-to-many accent conversion with Normalizing Flows

Add code
Nov 10, 2022
Viaarxiv icon

Text-free non-parallel many-to-many voice conversion using normalising flows

Add code
Mar 15, 2022
Figure 1 for Text-free non-parallel many-to-many voice conversion using normalising flows
Figure 2 for Text-free non-parallel many-to-many voice conversion using normalising flows
Figure 3 for Text-free non-parallel many-to-many voice conversion using normalising flows
Figure 4 for Text-free non-parallel many-to-many voice conversion using normalising flows
Viaarxiv icon

Enhancing audio quality for expressive Neural Text-to-Speech

Add code
Aug 13, 2021
Figure 1 for Enhancing audio quality for expressive Neural Text-to-Speech
Figure 2 for Enhancing audio quality for expressive Neural Text-to-Speech
Figure 3 for Enhancing audio quality for expressive Neural Text-to-Speech
Figure 4 for Enhancing audio quality for expressive Neural Text-to-Speech
Viaarxiv icon

Non-Autoregressive TTS with Explicit Duration Modelling for Low-Resource Highly Expressive Speech

Add code
Jun 25, 2021
Figure 1 for Non-Autoregressive TTS with Explicit Duration Modelling for Low-Resource Highly Expressive Speech
Figure 2 for Non-Autoregressive TTS with Explicit Duration Modelling for Low-Resource Highly Expressive Speech
Figure 3 for Non-Autoregressive TTS with Explicit Duration Modelling for Low-Resource Highly Expressive Speech
Figure 4 for Non-Autoregressive TTS with Explicit Duration Modelling for Low-Resource Highly Expressive Speech
Viaarxiv icon