Multi-output RNN-LSTM for multiple speaker speech synthesis with α-interpolation model.

Santiago Pascual Antonio Bonafonte

Published in: SSW (2016)

Keyphrases

recurrent neural networks
computational model
probabilistic model
probability distribution
pattern recognition
statistical model
theoretical framework
non stationary
genetic algorithm
input data
speech recognition
management system
prior knowledge
conceptual model
autoregressive
multiple models
speech synthesis