Predicted Phase Using Deep Neural Networks to Enhance Esophageal Speech.
Madiha AmarjoufFadoua BahjaJoseph Di MartinoMouhcine ChamiEl Hassan Ibn ElhajPublished in: AICV (2023)
Keyphrases
- neural network
- speech signal
- speech recognition
- pattern recognition
- automatic speech recognition
- artificial neural networks
- fuzzy logic
- speech quality
- preprocessing phase
- linear prediction
- back propagation
- vocal tract
- self organizing maps
- neural network model
- feed forward
- recurrent neural networks
- speech synthesis
- training process
- hidden markov models
- speaker identification
- speaker recognition
- expert systems
- neural nets
- multi layer
- multilayer perceptron
- non stationary
- activation function
- multi modal
- noisy environments
- spoken language
- phase information
- training data
- decision trees
- learning algorithm