Phoneme acquisition model based on vowel imitation using Recurrent Neural Network.
Hisashi KandaTetsuya OgataToru TakahashiKazunori KomataniHiroshi G. OkunoPublished in: IROS (2009)
Keyphrases
- recurrent neural networks
- speech synthesis
- feed forward
- neural network
- speech recognition
- recurrent networks
- prosodic features
- complex valued
- reservoir computing
- feedforward neural networks
- hidden layer
- artificial neural networks
- long short term memory
- neural model
- echo state networks
- vowel phonemes
- hebbian learning
- speech signal
- real time
- reinforcement learning
- nonlinear dynamic systems
- text to speech
- vocal tract
- genetic algorithm