Recurrent Timing Neural Networks for Joint F0-Localisation Based Speech Separation.
Stuart N. WrigleyGuy J. BrownPublished in: ICASSP (1) (2007)
Keyphrases
- neural network
- recurrent neural networks
- feed forward
- speech recognition
- back propagation
- pattern recognition
- speech signal
- fuzzy logic
- neural network model
- multilayer perceptron
- neural nets
- artificial neural networks
- spiking neural networks
- text to speech
- recurrent networks
- speaker recognition
- speech synthesis
- recognition engine
- emotion recognition
- fuzzy neural network
- fault diagnosis
- multi modal
- multi stream
- data sets
- hearing impaired
- multimodal interfaces
- adaptive resonance theory
- speaker identification
- spoken language
- activation function
- audio visual
- self organizing maps
- expert systems
- information retrieval