A Performance Evaluation of Several Deep Neural Networks for Reverberant Speech Separation.
Qingju LiuWenwu WangPhilip J. B. JacksonSaeid SafaviPublished in: ACSSC (2018)
Keyphrases
- speech signal
- neural network
- speech recognition
- sound source
- vocal tract
- automatic speech recognition
- pattern recognition
- speaker identification
- automatic speech recognition systems
- genetic algorithm
- noisy environments
- fuzzy logic
- multi layer
- neural nets
- back propagation
- linear prediction
- speaker recognition
- audio visual
- non stationary
- language acquisition
- deep learning
- text to speech
- fault diagnosis
- recognition engine
- learning algorithm
- adaptive resonance theory
- speech synthesis
- artificial neural networks
- hidden markov models
- dialogue system
- activation function
- network architecture
- training process
- fuzzy systems