Audio-Visual Speech Super-Resolution
Rudrabha Mukhopadhyay*, Sindhu B Hegde* , Vinay Namboodiri and C.V. Jawahar
IIIT Hyderabad Univ. of Bath
BMVC, 2021 (Oral)
[ Code ] | [ Demo Video ]
We present an audio-visual model for super-resolving very low-resolution speech inputs (example, 1kHz) at large scale-factors. In contrast to the existing audio-only speech super-resolution approaches, our method benefits from the visual stream, either the real-visual stream (if available), or the generated visual stream from our pseudo-visual network.
--- COMING SOON ---