On the use of the Watson mixture model for clustering-based under-determined blind source separation.
Ingrid JafariRoberto TogneriSven NordholmPublished in: INTERSPEECH (2014)
Keyphrases
- mixture model
- blind source separation
- component analysis
- independent component analysis
- gaussian mixture model
- non stationary
- probabilistic model
- em algorithm
- generative model
- model selection
- blind separation
- unsupervised learning
- language model
- expectation maximization
- maximum likelihood
- negative matrix factorization
- speech signal
- data sets
- probabilistic mixture model
- sparse representation
- co occurrence
- feature vectors