Paper: Jan 30,2016
cs.CV
ID:1601.08188
Lipreading with Long Short-Term Memory
Lipreading, i.e. speech recognition from visual-only recordings of a
speaker's face, can be achieved with a processing pipeline based solely on
neural networks, yielding significantly better accuracy than conventional
methods. Feed-forward and recurrent neural network layers (namely Long
Short-Term Memory; LSTM) are stacked to form a single structure which is
trained by back-propagating error gradients through all the layers. The
performance of such a stacked network was experimentally evaluated and compared
to a standard Support Vector Machine classifier using conventional computer
vision features (Eigenlips and Histograms of Oriented Gradients). The
evaluation was performed on data from 19 speakers of the publicly available
GRID corpus. With 51 different words to classify, we report a best word
accuracy on held-out evaluation speakers of 79.6% using the end-to-end neural
network-based solution (11.6% improvement over the best feature-based solution
evaluated).
🔗 View origin paper >>
Am I the publisher of this paper? I want to claim it
Claim
Paper Author: Michael Wand,Jan Koutník,Jürgen Schmidhuber
Leave an answer
Hot post
Popular Paper