Search

Adobe Media and Data Science Research (MDSR) Laboratory
Adobe Media and Data Science Research (MDSR) Laboratory
  • Impact
  • Research
  • People
  • Careers
Hush-Hush Speak: Speech Reconstruction Using Silent Videos
Speech Reconstruction is the task of recreation of speech using silent videos as input. In the literature, it is also referred to as …
Shashwat Uttam, Yaman Kumar Singla, Dhruva Sharawat, Mansi Aggarwal, Debanjan Mahata, Rajiv Ratn Shah, Amanda Stent
PDF
Harnessing AI for speech reconstruction using multiview silent video feed
Speechreading or lipreading is the technique of understanding and getting phonetic features from a speaker’s visual features such …
Yaman Kumar Singla, Mayank Aggarwal, Pratham Nawal, Shin'ichi Satoh, Rajiv Ratn Shah, Roger Zimmerman
PDF

© 2025 Adobe. All rights reserved.

Cite
Copy Download