Iterative Deep Neural Networks for Speaker-Independent Binaural Blind Speech Separation.
Qingju LiuYong XuPhilip J. B. JacksonWenwu WangPhilip ColemanPublished in: ICASSP (2018)
Keyphrases
- speaker independent
- speech recognition
- neural network
- speaker dependent
- speaker identification
- sound source
- speech signal
- hidden markov models
- pattern recognition
- speech recognizer
- digit recognition
- speech recognition systems
- acoustic models
- speech synthesis
- automatic speech recognition
- emotion classification
- speaker adaptation
- language model
- noisy environments
- spoken language
- gaussian mixture model
- broadcast news
- feature extraction
- probabilistic neural network
- speaker recognition
- emotional speech
- vocal tract
- deep learning
- training process
- image segmentation