Lip2AudSpec: Speech reconstruction from silent lip movements video.

Hassan Akbari Himani Arora Liangliang Cao Nima Mesgarani

Published in: CoRR (2017)

Keyphrases

visual speech
lip reading
visual speech recognition
mouth region
audio visual speech recognition
multimedia
motion features

real time
video frames
video sequences
video streams
video content
three dimensional

video data
broadcast news
hidden markov models
audio video
multi stream
speech recognition

dynamic textures
content based video retrieval
noisy environments
video shots
video database
image reconstruction