Alert button
Picture for Roberto Barra-Chicote

Roberto Barra-Chicote

Alert button

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

Feb 05, 2024
Álvaro Martín-Cortinas, Daniel Sáez-Trigueros, Iván Vallés-Pérez, Biel Tura-Vecino, Piotr Biliński, Mateusz Lajszczak, Grzegorz Beringer, Roberto Barra-Chicote, Jaime Lorenzo-Trueba

Viaarxiv icon

Creating New Voices using Normalizing Flows

Dec 22, 2023
Piotr Bilinski, Thomas Merritt, Abdelhamid Ezzerg, Kamil Pokora, Sebastian Cygert, Kayoko Yanagisawa, Roberto Barra-Chicote, Daniel Korzekwa

Viaarxiv icon

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

Jul 31, 2023
Guangyan Zhang, Thomas Merritt, Manuel Sam Ribeiro, Biel Tura-Vecino, Kayoko Yanagisawa, Kamil Pokora, Abdelhamid Ezzerg, Sebastian Cygert, Ammar Abbas, Piotr Bilinski, Roberto Barra-Chicote, Daniel Korzekwa, Jaime Lorenzo-Trueba

Figure 1 for Comparing normalizing flows and diffusion models for prosody and acoustic modelling in text-to-speech
Figure 2 for Comparing normalizing flows and diffusion models for prosody and acoustic modelling in text-to-speech
Figure 3 for Comparing normalizing flows and diffusion models for prosody and acoustic modelling in text-to-speech
Figure 4 for Comparing normalizing flows and diffusion models for prosody and acoustic modelling in text-to-speech
Viaarxiv icon

SCRAPS: Speech Contrastive Representations of Acoustic and Phonetic Spaces

Jul 23, 2023
Ivan Vallés-Pérez, Grzegorz Beringer, Piotr Bilinski, Gary Cook, Roberto Barra-Chicote

Figure 1 for SCRAPS: Speech Contrastive Representations of Acoustic and Phonetic Spaces
Figure 2 for SCRAPS: Speech Contrastive Representations of Acoustic and Phonetic Spaces
Figure 3 for SCRAPS: Speech Contrastive Representations of Acoustic and Phonetic Spaces
Figure 4 for SCRAPS: Speech Contrastive Representations of Acoustic and Phonetic Spaces
Viaarxiv icon

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

Nov 10, 2022
Abdelhamid Ezzerg, Thomas Merritt, Kayoko Yanagisawa, Piotr Bilinski, Magdalena Proszewska, Kamil Pokora, Renard Korzeniowski, Roberto Barra-Chicote, Daniel Korzekwa

Figure 1 for Remap, warp and attend: Non-parallel many-to-many accent conversion with Normalizing Flows
Figure 2 for Remap, warp and attend: Non-parallel many-to-many accent conversion with Normalizing Flows
Figure 3 for Remap, warp and attend: Non-parallel many-to-many accent conversion with Normalizing Flows
Figure 4 for Remap, warp and attend: Non-parallel many-to-many accent conversion with Normalizing Flows
Viaarxiv icon

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

Nov 04, 2022
Xin Zhang, Iván Vallés-Pérez, Andreas Stolcke, Chengzhu Yu, Jasha Droppo, Olabanji Shonibare, Roberto Barra-Chicote, Venkatesh Ravichandran

Figure 1 for Stutter-TTS: Controlled Synthesis and Improved Recognition of Stuttered Speech
Figure 2 for Stutter-TTS: Controlled Synthesis and Improved Recognition of Stuttered Speech
Figure 3 for Stutter-TTS: Controlled Synthesis and Improved Recognition of Stuttered Speech
Figure 4 for Stutter-TTS: Controlled Synthesis and Improved Recognition of Stuttered Speech
Viaarxiv icon

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

Jul 04, 2022
Magdalena Proszewska, Grzegorz Beringer, Daniel Sáez-Trigueros, Thomas Merritt, Abdelhamid Ezzerg, Roberto Barra-Chicote

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

Apr 06, 2022
Yogesh Virkar, Marcello Federico, Robert Enyedi, Roberto Barra-Chicote

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

Mar 15, 2022
Thomas Merritt, Abdelhamid Ezzerg, Piotr Biliński, Magdalena Proszewska, Kamil Pokora, Roberto Barra-Chicote, Daniel Korzekwa

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

Feb 16, 2022
Adam Gabryś, Goeric Huybrechts, Manuel Sam Ribeiro, Chung-Ming Chien, Julian Roth, Giulia Comini, Roberto Barra-Chicote, Bartek Perz, Jaime Lorenzo-Trueba

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