Picture for Alexandra Markó

Alexandra Markó

Adaptation of Tacotron2-based Text-To-Speech for Articulatory-to-Acoustic Mapping using Ultrasound Tongue Imaging

Add code
Jul 26, 2021
Figure 1 for Adaptation of Tacotron2-based Text-To-Speech for Articulatory-to-Acoustic Mapping using Ultrasound Tongue Imaging
Figure 2 for Adaptation of Tacotron2-based Text-To-Speech for Articulatory-to-Acoustic Mapping using Ultrasound Tongue Imaging
Figure 3 for Adaptation of Tacotron2-based Text-To-Speech for Articulatory-to-Acoustic Mapping using Ultrasound Tongue Imaging
Figure 4 for Adaptation of Tacotron2-based Text-To-Speech for Articulatory-to-Acoustic Mapping using Ultrasound Tongue Imaging
Viaarxiv icon

Speech Synthesis from Text and Ultrasound Tongue Image-based Articulatory Input

Add code
Jul 05, 2021
Figure 1 for Speech Synthesis from Text and Ultrasound Tongue Image-based Articulatory Input
Figure 2 for Speech Synthesis from Text and Ultrasound Tongue Image-based Articulatory Input
Figure 3 for Speech Synthesis from Text and Ultrasound Tongue Image-based Articulatory Input
Figure 4 for Speech Synthesis from Text and Ultrasound Tongue Image-based Articulatory Input
Viaarxiv icon

Improving Neural Silent Speech Interface Models by Adversarial Training

Add code
Apr 23, 2021
Figure 1 for Improving Neural Silent Speech Interface Models by Adversarial Training
Figure 2 for Improving Neural Silent Speech Interface Models by Adversarial Training
Figure 3 for Improving Neural Silent Speech Interface Models by Adversarial Training
Figure 4 for Improving Neural Silent Speech Interface Models by Adversarial Training
Viaarxiv icon