Picture for Roberto Barra-Chicote

Roberto Barra-Chicote

Enhancing the Stability of LLM-based Speech Generation Systems through Self-Supervised Representations

Add code
Feb 05, 2024
Viaarxiv icon

Creating New Voices using Normalizing Flows

Add code
Dec 22, 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

SCRAPS: Speech Contrastive Representations of Acoustic and Phonetic Spaces

Add code
Jul 23, 2023
Viaarxiv icon

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

Add code
Nov 10, 2022
Viaarxiv icon

Stutter-TTS: Controlled Synthesis and Improved Recognition of Stuttered Speech

Add code
Nov 04, 2022
Viaarxiv icon

GlowVC: Mel-spectrogram space disentangling model for language-independent text-free voice conversion

Add code
Jul 04, 2022
Figure 1 for GlowVC: Mel-spectrogram space disentangling model for language-independent text-free voice conversion
Figure 2 for GlowVC: Mel-spectrogram space disentangling model for language-independent text-free voice conversion
Figure 3 for GlowVC: Mel-spectrogram space disentangling model for language-independent text-free voice conversion
Figure 4 for GlowVC: Mel-spectrogram space disentangling model for language-independent text-free voice conversion
Viaarxiv icon

Prosodic Alignment for off-screen automatic dubbing

Add code
Apr 06, 2022
Figure 1 for Prosodic Alignment for off-screen automatic dubbing
Figure 2 for Prosodic Alignment for off-screen automatic dubbing
Figure 3 for Prosodic Alignment for off-screen automatic dubbing
Figure 4 for Prosodic Alignment for off-screen automatic dubbing
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

Voice Filter: Few-shot text-to-speech speaker adaptation using voice conversion as a post-processing module

Add code
Feb 16, 2022
Figure 1 for Voice Filter: Few-shot text-to-speech speaker adaptation using voice conversion as a post-processing module
Figure 2 for Voice Filter: Few-shot text-to-speech speaker adaptation using voice conversion as a post-processing module
Figure 3 for Voice Filter: Few-shot text-to-speech speaker adaptation using voice conversion as a post-processing module
Figure 4 for Voice Filter: Few-shot text-to-speech speaker adaptation using voice conversion as a post-processing module
Viaarxiv icon