Deep Attractor Networks for Speaker Re-Identification and Blind Source Separation.
Lukas DrudeThilo von NeumannReinhold Haeb-UmbachPublished in: ICASSP (2018)
Keyphrases
- blind source separation
- component analysis
- independent component analysis
- non stationary
- source separation
- blind separation
- adaptive particle swarm optimization
- negative matrix factorization
- natural gradient
- mixing matrix
- algebraic equations
- speech signal
- eigenvalue decomposition
- dynamical systems
- speech recognition
- independent components
- source signals
- pattern recognition
- face recognition
- data sets
- factor analysis
- sparse representation
- signal processing
- information retrieval systems
- principal component analysis
- hidden markov models