Login / Signup
Improving Trajectory Modelling for DNN-Based Speech Synthesis by Using Stacked Bottleneck Features and Minimum Generation Error Training.
Zhizheng Wu
Simon King
Published in:
IEEE ACM Trans. Audio Speech Lang. Process. (2016)
Keyphrases
</>
speech synthesis
training process
feature vectors
feature extraction
low level
feature space
image features
co occurrence
feature set
text to speech
speech recognition
training and testing data
image processing
extracted features
error rate
face detection
training examples
supervised learning