Deep learning of split temporal context for automatic speech recognition.

Moez Baccouche Benoit Besset Patrice Collen Olivier Le Blouch

Published in: ICASSP (2014)

Keyphrases

deep learning
automatic speech recognition
temporal context
speech recognition
spatial context
temporal information
hidden markov models
unsupervised learning
machine learning
audio visual
speech signal
mental models
data mining
weakly supervised
spatial information
semi supervised
higher order
pattern recognition