No abstract

Figure 1: We address the problem of generating speech from silent lip videos for any speaker in the wild. Previous works train either on large amounts of data of isolated speakers or in laboratory settings with a limited vocabulary. Conversely, we can generate speech for the lip movements of arbitrary identities in any voice without additional speaker-specific fine-tuning. Our new VAE-GAN approach allows us to learn strong audio-visual associations despite the ambiguous nature of the task.

No abstract

No abstract

No abstract