Acoustic Modeling Using Adversarially Trained Variational Recurrent Neural Network for Speech Synthesis.
Joun Yeop LeeSung Jun CheonByoung Jin ChoiNam Soo KimEunwoo SongPublished in: INTERSPEECH (2018)
Keyphrases
- recurrent neural networks
- speech synthesis
- echo state networks
- prosodic features
- speech recognition
- recurrent networks
- text to speech
- complex valued
- neural network
- feed forward
- feedforward neural networks
- reservoir computing
- hidden layer
- artificial neural networks
- nonlinear dynamic systems
- vocal tract
- neural model
- semi supervised
- image segmentation
- information retrieval