Deep Learning Based Binaural Speech Separation in Reverberant Environments.
Xueliang ZhangDeLiang WangPublished in: IEEE ACM Trans. Audio Speech Lang. Process. (2017)
Keyphrases
- deep learning
- speech signal
- sound source
- speech recognition
- unsupervised learning
- unsupervised feature learning
- machine learning
- non stationary
- mental models
- weakly supervised
- restricted boltzmann machine
- deep architectures
- higher order
- hidden markov models
- probabilistic model
- pairwise
- multiscale
- information retrieval