Login / Signup
Noise-Resilient Training Method for Face Landmark Generation From Speech.
Sefik Emre Eskimez
Ross K. Maddox
Chenliang Xu
Zhiyao Duan
Published in:
IEEE ACM Trans. Audio Speech Lang. Process. (2020)
Keyphrases
</>
noisy data
input data
preprocessing
pairwise
significant improvement
objective function
training samples
hybrid method
training process
noisy images
segmentation method
edge detection
supervised learning
detection method
high accuracy
training phase
image noise