Picture for Paul Dixon

Paul Dixon

Improving vision-inspired keyword spotting using dynamic module skipping in streaming conformer encoder

Add code
Aug 31, 2023
Viaarxiv icon

Flexible Keyword Spotting based on Homogeneous Audio-Text Embedding

Add code
Aug 12, 2023
Viaarxiv icon

Modality Dropout for Improved Performance-driven Talking Faces

Add code
May 27, 2020
Figure 1 for Modality Dropout for Improved Performance-driven Talking Faces
Figure 2 for Modality Dropout for Improved Performance-driven Talking Faces
Figure 3 for Modality Dropout for Improved Performance-driven Talking Faces
Figure 4 for Modality Dropout for Improved Performance-driven Talking Faces
Viaarxiv icon

Speaker-Independent Speech-Driven Visual Speech Synthesis using Domain-Adapted Acoustic Models

Add code
May 15, 2019
Figure 1 for Speaker-Independent Speech-Driven Visual Speech Synthesis using Domain-Adapted Acoustic Models
Figure 2 for Speaker-Independent Speech-Driven Visual Speech Synthesis using Domain-Adapted Acoustic Models
Figure 3 for Speaker-Independent Speech-Driven Visual Speech Synthesis using Domain-Adapted Acoustic Models
Viaarxiv icon