Phonetic visualization for speech training system by using neural network.
Itaru NagayamaNorio AkamatsuToshiki YoshinoPublished in: ICSLP (1994)
Keyphrases
- neural network
- speech recognition
- training algorithm
- training process
- self organizing maps
- acoustic models
- feedforward neural networks
- neural network training
- feed forward neural networks
- multi layer perceptron
- back propagation
- spoken term detection
- speech recognizer
- pattern recognition
- spoken document retrieval
- recurrent networks
- training patterns
- test set
- neural network structure
- backpropagation algorithm
- hearing impaired
- genetic algorithm
- training set
- automatic speech recognition
- visualization tool
- speaker independent
- neural network is trained
- network architecture
- supervised learning
- train a neural network
- recurrent neural networks
- feed forward
- noisy environments
- information retrieval
- text to speech
- artificial neural networks
- activation function
- probabilistic model
- audio visual
- fuzzy logic
- multi layer
- neural network model