Login / Signup
Improving Trajectory Modelling for DNN-based Speech Synthesis by using Stacked Bottleneck Features and Minimum Trajectory Error Training.
Zhizheng Wu
Simon King
Published in:
CoRR (2016)
Keyphrases
</>
speech synthesis
training process
feature extraction
feature vectors
co occurrence
training examples
error rate
low level
feature set
trajectory data
learning algorithm
image features
speech recognition
training phase
linear svm
movement patterns