Binaural Reverberant Speech Separation Based on Deep Neural Networks.
Xueliang ZhangDeLiang WangPublished in: INTERSPEECH (2017)
Keyphrases
- speech signal
- sound source
- neural network
- speech recognition
- automatic speech recognition
- vocal tract
- speaker identification
- pattern recognition
- hidden markov models
- noisy environments
- non stationary
- artificial neural networks
- genetic algorithm
- speaker recognition
- fuzzy logic
- multi layer
- audio features
- natural language
- data sets
- blind source separation
- fuzzy systems
- network architecture
- feed forward
- neural network model
- fault diagnosis