Alert button
Picture for Dominik Roblek

Dominik Roblek

Alert button

SEANet: A Multi-modal Speech Enhancement Network

Oct 01, 2020
Marco Tagliasacchi, Yunpeng Li, Karolis Misiunas, Dominik Roblek

Figure 1 for SEANet: A Multi-modal Speech Enhancement Network
Figure 2 for SEANet: A Multi-modal Speech Enhancement Network
Figure 3 for SEANet: A Multi-modal Speech Enhancement Network
Figure 4 for SEANet: A Multi-modal Speech Enhancement Network
Viaarxiv icon

Learning to Denoise Historical Music

Aug 05, 2020
Yunpeng Li, Beat Gfeller, Marco Tagliasacchi, Dominik Roblek

Figure 1 for Learning to Denoise Historical Music
Figure 2 for Learning to Denoise Historical Music
Figure 3 for Learning to Denoise Historical Music
Figure 4 for Learning to Denoise Historical Music
Viaarxiv icon

Training Keyword Spotters with Limited and Synthesized Speech Data

Jan 31, 2020
James Lin, Kevin Kilgour, Dominik Roblek, Matthew Sharifi

Figure 1 for Training Keyword Spotters with Limited and Synthesized Speech Data
Figure 2 for Training Keyword Spotters with Limited and Synthesized Speech Data
Figure 3 for Training Keyword Spotters with Limited and Synthesized Speech Data
Figure 4 for Training Keyword Spotters with Limited and Synthesized Speech Data
Viaarxiv icon

Learning audio representations via phase prediction

Oct 25, 2019
Félix de Chaumont Quitry, Marco Tagliasacchi, Dominik Roblek

Figure 1 for Learning audio representations via phase prediction
Figure 2 for Learning audio representations via phase prediction
Figure 3 for Learning audio representations via phase prediction
Viaarxiv icon

SPICE: Self-supervised Pitch Estimation

Oct 25, 2019
Beat Gfeller, Christian Frank, Dominik Roblek, Matt Sharifi, Marco Tagliasacchi, Mihajlo Velimirović

Figure 1 for SPICE: Self-supervised Pitch Estimation
Figure 2 for SPICE: Self-supervised Pitch Estimation
Figure 3 for SPICE: Self-supervised Pitch Estimation
Figure 4 for SPICE: Self-supervised Pitch Estimation
Viaarxiv icon

From Here to There: Video Inbetweening Using Direct 3D Convolutions

Jun 04, 2019
Yunpeng Li, Dominik Roblek, Marco Tagliasacchi

Figure 1 for From Here to There: Video Inbetweening Using Direct 3D Convolutions
Figure 2 for From Here to There: Video Inbetweening Using Direct 3D Convolutions
Figure 3 for From Here to There: Video Inbetweening Using Direct 3D Convolutions
Figure 4 for From Here to There: Video Inbetweening Using Direct 3D Convolutions
Viaarxiv icon

Self-supervised audio representation learning for mobile devices

May 24, 2019
Marco Tagliasacchi, Beat Gfeller, Félix de Chaumont Quitry, Dominik Roblek

Figure 1 for Self-supervised audio representation learning for mobile devices
Figure 2 for Self-supervised audio representation learning for mobile devices
Figure 3 for Self-supervised audio representation learning for mobile devices
Figure 4 for Self-supervised audio representation learning for mobile devices
Viaarxiv icon

An Empirical Study of Generative Models with Encoders

Dec 19, 2018
Paul K. Rubenstein, Yunpeng Li, Dominik Roblek

Figure 1 for An Empirical Study of Generative Models with Encoders
Figure 2 for An Empirical Study of Generative Models with Encoders
Figure 3 for An Empirical Study of Generative Models with Encoders
Figure 4 for An Empirical Study of Generative Models with Encoders
Viaarxiv icon