A Mixture of Recurrent Neural Networks for Speaker Normalisation.
Edmondo TrentinDiego GiulianiPublished in: Neural Comput. Appl. (2001)
Keyphrases
- recurrent neural networks
- mixture model
- neural network
- feed forward
- recurrent networks
- complex valued
- reservoir computing
- echo state networks
- speech recognition
- speaker recognition
- long short term memory
- speaker verification
- feedforward neural networks
- neural model
- audio visual
- artificial neural networks
- gaussian mixture model
- hebbian learning
- speaker identification
- probabilistic model
- speaker diarization
- nonlinear dynamic systems
- cascade correlation
- real valued
- expectation maximization
- fuzzy logic
- neural models
- long term
- genetic algorithm