Parallel WaveNet conditioned on VAE latent vectors
Recently the state-of-the-art text-to-speech synthesis systems have shifted to a two-model approach: a sequence-to-sequence model to predict a representation of speech (typically mel-spectrograms), followed by a 'neural vocoder' model which produces the time-domain speech waveform from this intermediate speech representation. This approach is capable of synthesizing speech that is confusable with natural speech recordings... (read more)
PDFDatasets
Add Datasets
introduced or used in this paper
Results from the Paper
Submit
results from this paper
to get state-of-the-art GitHub badges and help the
community compare results to other papers.
Sigmoid Activation
Tanh Activation
Highway Layer
Dilated Causal Convolution
Mixture of Logistic Distributions
Additive Attention
ReLU
Convolution
Griffin-Lim Algorithm
Highway Network
Max Pooling
Batch Normalization
Dropout
Dense Connections
BiGRU
GRU
WaveNet
VAE
Residual Connection
CBHG
Residual GRU
Tacotron