Deep Learning for Talker-Dependent Reverberant Speaker Separation: An Empirical Study.
Masood DelfarahDeLiang WangPublished in: IEEE ACM Trans. Audio Speech Lang. Process. (2019)
Keyphrases
- deep learning
- speech signal
- unsupervised learning
- unsupervised feature learning
- sound source
- speech recognition
- machine learning
- deep architectures
- weakly supervised
- restricted boltzmann machine
- mental models
- domain specific
- maximum likelihood
- object detection
- data sets
- object recognition
- pattern recognition
- clustering algorithm