Lombard speech synthesis using long short-term memory recurrent neural networks.
Bajibabu BollepalliManu AiraksinenPaavo AlkuPublished in: ICASSP (2017)
Keyphrases
- recurrent neural networks
- speech synthesis
- long short term memory
- speech recognition
- text to speech
- feed forward
- vocal tract
- neural network
- prosodic features
- reservoir computing
- complex valued
- recurrent networks
- neural model
- artificial neural networks
- cascade correlation
- nonlinear dynamic systems
- feedforward neural networks
- echo state networks
- speech corpus
- hebbian learning
- model selection
- fuzzy controller
- hidden markov models
- bayesian networks