Login / Signup
Investigation of mixture splitting concept for training linear bottlenecks of deep neural network acoustic models.
Muhammad Ali Tahir
Simon Wiesler
Ralf Schlüter
Hermann Ney
Published in:
ICASSP (2015)
Keyphrases
</>
neural network
acoustic models
training process
speech recognition
hidden markov models
back propagation
pattern recognition
training set
supervised learning
data sets
machine learning
speech recognizer
mixture model